[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75DTM1E1E4PBJCD8XASPE2S":3,"skill-same:01M75DTM1E1E4PBJCD8XASPE2S":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M75DTM1E1E4PBJCD8XASPE2S","manifest",null,"Smart LLM Router for OpenClaw. Save up to 70% by routing every request to the right model. No coding required.","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbrunobuddy\u002Fmanifest-build\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: manifest\ndescription: Smart LLM Router for OpenClaw. Save up to 70% by routing every request to the right model. No coding required.\nmetadata: {\"openclaw\":{\"requires\":{\"bins\":[\"openclaw\"],\"env\":[\"MANIFEST_API_KEY\"],\"config\":[\"plugins.entries.manifest.config.apiKey\"]},\"primaryEnv\":\"MANIFEST_API_KEY\",\"homepage\":\"https:\u002F\u002Fgithub.com\u002Fmnfst\u002Fmanifest\"}}\n---\n\n# Manifest — LLM Router & Observability for OpenClaw\n\nManifest is an OpenClaw plugin that:\n\n- **Routes every request** to the most cost-effective model via a 23-dimension scoring algorithm (\u003C2ms latency)\n- **Tracks costs and tokens** in a real-time dashboard\n- **Sets limits** with email alerts and hard spending caps\n\nSource: [github.com\u002Fmnfst\u002Fmanifest](https:\u002F\u002Fgithub.com\u002Fmnfst\u002Fmanifest) — MIT licensed. Homepage: [manifest.build](https:\u002F\u002Fmanifest.build)\n\n## Setup (Cloud — default)\n\nThree commands, no coding:\n\n```bash\nopenclaw plugins install manifest\nopenclaw config set plugins.entries.manifest.config.apiKey \"mnfst_YOUR_KEY\"\nopenclaw gateway restart\n```\n\nGet the API key at [app.manifest.build](https:\u002F\u002Fapp.manifest.build) → create an account → create an agent → copy the `mnfst_*` key.\n\nAfter restart, the plugin auto-configures:\n\n- Adds `manifest\u002Fauto` to the model allowlist (does not change your current default)\n- Injects the `manifest` provider into `~\u002F.openclaw\u002Fopenclaw.json`\n- Starts exporting OTLP telemetry to `app.manifest.build`\n- Exposes three agent tools: `manifest_usage`, `manifest_costs`, `manifest_health`\n\nDashboard at [app.manifest.build](https:\u002F\u002Fapp.manifest.build). Telemetry arrives within 10-30 seconds (batched OTLP export).\n\n### Verify connection\n\n```bash\nopenclaw manifest\n```\n\nShows: mode, endpoint reachability, auth validity, agent name.\n\n## Configuration Changes\n\nOn plugin registration, Manifest writes to these files:\n\n| File                                            | Change                                                                                                      | Reversible                                  |\n| ----------------------------------------------- | ----------------------------------------------------------------------------------------------------------- | ------------------------------------------- |\n| `~\u002F.openclaw\u002Fopenclaw.json`                     | Adds `models.providers.manifest` provider entry; adds `manifest\u002Fauto` to `agents.defaults.models` allowlist | Yes — `openclaw plugins uninstall manifest` |\n| `~\u002F.openclaw\u002Fagents\u002F*\u002Fagent\u002Fauth-profiles.json` | Adds `manifest:default` auth profile                                                                        | Yes — uninstall removes it                  |\n| `~\u002F.openclaw\u002Fmanifest\u002Fconfig.json`              | Stores auto-generated API key (local mode only, file mode 0600)                                             | Yes — delete `~\u002F.openclaw\u002Fmanifest\u002F`        |\n| `~\u002F.openclaw\u002Fmanifest\u002Fmanifest.db`              | SQLite database (local mode only)                                                                           | Yes — delete the file                       |\n\nNo other files are modified. The plugin does not change your current default model.\n\n## Install Provenance\n\n`openclaw plugins install manifest` installs the [`manifest`](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fmanifest) npm package.\n\n- **Source**: [github.com\u002Fmnfst\u002Fmanifest](https:\u002F\u002Fgithub.com\u002Fmnfst\u002Fmanifest) (`packages\u002Fopenclaw-plugin\u002F`)\n- **License**: MIT\n- **Author**: MNFST Inc.\n\nVerify before installing:\n\n```bash\nnpm view manifest repository.url\nnpm view manifest dist.integrity\n```\n\n## Setup (Local — offline alternative)\n\nUse local mode only when data must never leave the machine.\n\n```bash\nopenclaw plugins install manifest\nopenclaw config set plugins.entries.manifest.config.mode local\nopenclaw gateway restart\n```\n\nDashboard opens at **http:\u002F\u002F127.0.0.1:2099**. Data stored locally in `~\u002F.openclaw\u002Fmanifest\u002Fmanifest.db`. No account or API key needed.\n\nTo expose over Tailscale (requires Tailscale on both devices, only accessible within your Tailnet): `tailscale serve --bg 2099`\n\n## What Manifest Answers\n\nManifest answers these questions about your OpenClaw agents — via the dashboard or directly in-conversation via agent tools:\n\n**Spending & budget**\n\n- How much have I spent today \u002F this week \u002F this month?\n- What's my cost breakdown by model?\n- Which model consumes the biggest share of my budget?\n- Am I approaching my spending limit?\n\n**Token consumption**\n\n- How many tokens has my agent used (input vs. output)?\n- What's my token trend compared to the previous period?\n- How much cache am I reading vs. writing?\n\n**Activity & performance**\n\n- How many LLM calls has my agent made?\n- How long do LLM calls take (latency)?\n- Are there errors or rate limits occurring? What are the error messages?\n- Which skills\u002Ftools are running and how often?\n\n**Routing intelligence**\n\n- What routing tier (simple\u002Fstandard\u002Fcomplex\u002Freasoning) was each request assigned?\n- Why was a specific tier chosen?\n- What model pricing is available across all providers?\n\n**Connectivity**\n\n- Is Manifest connected and healthy?\n- Is telemetry flowing correctly?\n\n## Agent Tools\n\nThree tools are available to the agent in-conversation:\n\n| Tool              | Trigger phrases                                 | What it returns                                                             |\n| ----------------- | ----------------------------------------------- | --------------------------------------------------------------------------- |\n| `manifest_usage`  | \"how many tokens\", \"token usage\", \"consumption\" | Total, input, output, cache-read tokens + action count for today\u002Fweek\u002Fmonth |\n| `manifest_costs`  | \"how much spent\", \"costs\", \"money burned\"       | Cost breakdown by model in USD for today\u002Fweek\u002Fmonth                         |\n| `manifest_health` | \"is monitoring working\", \"connectivity test\"    | Endpoint reachable, auth valid, agent name, status                          |\n\nEach accepts a `period` parameter: `\"today\"`, `\"week\"`, or `\"month\"`.\n\nAll three tools are read-only — they query the agent's own usage data and never send message content.\n\n## LLM Routing\n\nWhen the model is set to `manifest\u002Fauto`, the router scores each conversation across 23 dimensions and assigns one of 4 tiers:\n\n| Tier          | Use case                                | Examples                                                |\n| ------------- | --------------------------------------- | ------------------------------------------------------- |\n| **Simple**    | Greetings, confirmations, short lookups | \"hi\", \"yes\", \"what time is it\"                          |\n| **Standard**  | General tasks, balanced quality\u002Fcost    | \"summarize this\", \"write a test\"                        |\n| **Complex**   | Multi-step reasoning, nuanced analysis  | \"compare these architectures\", \"debug this stack trace\" |\n| **Reasoning** | Formal logic, proofs, critical planning | \"prove this theorem\", \"design a migration strategy\"     |\n\nEach tier maps to a model. Default models are auto-assigned per provider, but overridable in the dashboard under **Routing**.\n\nShort-circuit rules:\n\n- Messages \u003C50 chars with no tools → **Simple**\n- Formal logic keywords → **Reasoning**\n- Tools present → floor at **Standard**\n- Context >50k tokens → floor at **Complex**\n\n## Dashboard Pages\n\n| Page             | What it shows                                                                 |\n| ---------------- | ----------------------------------------------------------------------------- |\n| **Workspace**    | All connected agents as cards with sparkline activity charts                  |\n| **Overview**     | Per-agent cost, tokens, messages with trend badges and time-series charts     |\n| **Messages**     | Full paginated message log with filters (status, model, cost range)           |\n| **Routing**      | 4-tier model config, provider connections, enable\u002Fdisable routing             |\n| **Limits**       | Email alerts and hard spending caps (tokens or cost, per hour\u002Fday\u002Fweek\u002Fmonth) |\n| **Settings**     | Agent rename, delete, OTLP key management                                     |\n| **Model Prices** | Sortable table of 300+ model prices across all providers                      |\n\n## Supported Providers\n\nAnthropic, OpenAI, Google Gemini, DeepSeek, xAI, Mistral AI, Qwen, MiniMax, Kimi, Amazon Nova, Z.ai, OpenRouter, Ollama. 300+ models total.\n\n## Uninstall\n\n```bash\nopenclaw plugins uninstall manifest\nopenclaw gateway restart\n```\n\nThis removes the plugin, provider config, and auth profiles. After uninstalling, `manifest\u002Fauto` is no longer available. If any agent uses it, switch to another model.\n\n## Troubleshooting\n\n**Telemetry not appearing**: The gateway batches OTLP data every 10-30 seconds. Wait, then check `openclaw manifest` for connection status.\n\n**Auth errors in cloud mode**: Verify the API key starts with `mnfst_` and matches the key in the dashboard under Settings → Agent setup.\n\n**Port conflict in local mode**: If port 2099 is busy, the plugin checks if the existing process is Manifest and reuses it. To change the port: `openclaw config set plugins.entries.manifest.config.port \u003CPORT>`.\n\n**Plugin conflicts**: Manifest conflicts with the built-in `diagnostics-otel` plugin. Disable it before enabling Manifest.\n\n**After backend restart**: Always restart the gateway too (`openclaw gateway restart`) — the OTLP pipeline doesn't auto-reconnect.\n\n## Privacy\n\n### External Endpoints\n\n| Endpoint                            | When                               | Data Sent                                                                                                 |\n| ----------------------------------- | ---------------------------------- | --------------------------------------------------------------------------------------------------------- |\n| `{endpoint}\u002Fv1\u002Ftraces`              | Every LLM call (batched 10-30s)    | OTLP spans (see fields below)                                                                             |\n| `{endpoint}\u002Fv1\u002Fmetrics`             | Every 10-30s                       | Counters: request count, token totals, tool call counts — grouped by model\u002Fprovider                       |\n| `{endpoint}\u002Fapi\u002Fv1\u002Frouting\u002Fresolve` | Only when model is `manifest\u002Fauto` | Last 10 non-system\u002Fnon-developer messages (`{role, content}` only)                                        |\n| `https:\u002F\u002Feu.i.posthog.com`          | On plugin register                 | Hashed machine ID, OS, Node version, plugin version, mode. No PII. Opt out: `MANIFEST_TELEMETRY_OPTOUT=1` |\n\n### OTLP Span Fields\n\nExhaustive list of attributes sent per span:\n\n- `openclaw.session.key` — opaque session identifier\n- `openclaw.message.channel` — message channel name\n- `gen_ai.request.model` — model name (e.g. \"claude-sonnet-4-20250514\")\n- `gen_ai.system` — provider name (e.g. \"anthropic\")\n- `gen_ai.usage.input_tokens` — integer\n- `gen_ai.usage.output_tokens` — integer\n- `gen_ai.usage.cache_read_input_tokens` — integer\n- `gen_ai.usage.cache_creation_input_tokens` — integer\n- `openclaw.agent.name` — agent identifier\n- `tool.name` — tool name string\n- `tool.success` — boolean\n- `manifest.routing.tier` — routing tier (if routed)\n- `manifest.routing.reason` — routing reason (if routed)\n- Error status: agent errors truncated to 500 chars; tool errors include `event.error.message` untruncated\n\n**Not collected**: user prompts, assistant responses, tool input\u002Foutput arguments, file contents, or any message body.\n\n### Routing Data\n\n- Only active when model is `manifest\u002Fauto`\n- Excludes messages with `role: \"system\"` or `role: \"developer\"`\n- Sends only `{role, content}` — all other message properties are stripped (`routing.ts:77`)\n- 3-second timeout, non-blocking\n- To avoid sending content: disable routing in the dashboard or set a fixed model\n\n### Credential Storage\n\n- **Cloud mode**: API key stored in `~\u002F.openclaw\u002Fopenclaw.json` under `plugins.entries.manifest.config.apiKey` (managed by OpenClaw's standard plugin config)\n- **Local mode**: auto-generated key stored in `~\u002F.openclaw\u002Fmanifest\u002Fconfig.json` with file mode `0600`\n\n### Local Mode\n\nAll data stays on your machine. No external calls except optional PostHog analytics (opt out with `MANIFEST_TELEMETRY_OPTOUT=1`).\n","# Manifest — LLM Router & Observability for OpenClaw\n\nManifest is an OpenClaw plugin that:\n\n- **Routes every request** to the most cost-effective model via a 23-dimension scoring algorithm (\u003C2ms latency)\n- **Tracks costs and tokens** in a real-time dashboard\n- **Sets limits** with email alerts and hard spending caps\n\nSource: [github.com\u002Fmnfst\u002Fmanifest](https:\u002F\u002Fgithub.com\u002Fmnfst\u002Fmanifest) — MIT licensed. Homepage: [manifest.build](https:\u002F\u002Fmanifest.build)\n\n## Setup (Cloud — default)\n\nThree commands, no coding:\n\n```bash\nopenclaw plugins install manifest\nopenclaw config set plugins.entries.manifest.config.apiKey \"mnfst_YOUR_KEY\"\nopenclaw gateway restart\n```\n\nGet the API key at [app.manifest.build](https:\u002F\u002Fapp.manifest.build) → create an account → create an agent → copy the `mnfst_*` key.\n\nAfter restart, the plugin auto-configures:\n\n- Adds `manifest\u002Fauto` to the model allowlist (does not change your current default)\n- Injects the `manifest` provider into `~\u002F.openclaw\u002Fopenclaw.json`\n- Starts exporting OTLP telemetry to `app.manifest.build`\n- Exposes three agent tools: `manifest_usage`, `manifest_costs`, `manifest_health`\n\nDashboard at [app.manifest.build](https:\u002F\u002Fapp.manifest.build). Telemetry arrives within 10-30 seconds (batched OTLP export).\n\n### Verify connection\n\n```bash\nopenclaw manifest\n```\n\nShows: mode, endpoint reachability, auth validity, agent name.\n\n## Configuration Changes\n\nOn plugin registration, Manifest writes to these files:\n\n| File                                            | Change                                                                                                      | Reversible                                  |\n| ----------------------------------------------- | ----------------------------------------------------------------------------------------------------------- | ------------------------------------------- |\n| `~\u002F.openclaw\u002Fopenclaw.json`                     | Adds `models.providers.manifest` provider entry; adds `manifest\u002Fauto` to `agents.defaults.models` allowlist | Yes — `openclaw plugins uninstall manifest` |\n| `~\u002F.openclaw\u002Fagents\u002F*\u002Fagent\u002Fauth-profiles.json` | Adds `manifest:default` auth profile                                                                        | Yes — uninstall removes it                  |\n| `~\u002F.openclaw\u002Fmanifest\u002Fconfig.json`              | Stores auto-generated API key (local mode only, file mode 0600)                                             | Yes — delete `~\u002F.openclaw\u002Fmanifest\u002F`        |\n| `~\u002F.openclaw\u002Fmanifest\u002Fmanifest.db`              | SQLite database (local mode only)                                                                           | Yes — delete the file                       |\n\nNo other files are modified. The plugin does not change your current default model.\n\n## Install Provenance\n\n`openclaw plugins install manifest` installs the [`manifest`](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fmanifest) npm package.\n\n- **Source**: [github.com\u002Fmnfst\u002Fmanifest](https:\u002F\u002Fgithub.com\u002Fmnfst\u002Fmanifest) (`packages\u002Fopenclaw-plugin\u002F`)\n- **License**: MIT\n- **Author**: MNFST Inc.\n\nVerify before installing:\n\n```bash\nnpm view manifest repository.url\nnpm view manifest dist.integrity\n```\n\n## Setup (Local — offline alternative)\n\nUse local mode only when data must never leave the machine.\n\n```bash\nopenclaw plugins install manifest\nopenclaw config set plugins.entries.manifest.config.mode local\nopenclaw gateway restart\n```\n\nDashboard opens at **http:\u002F\u002F127.0.0.1:2099**. Data stored locally in `~\u002F.openclaw\u002Fmanifest\u002Fmanifest.db`. No account or API key needed.\n\nTo expose over Tailscale (requires Tailscale on both devices, only accessible within your Tailnet): `tailscale serve --bg 2099`\n\n## What Manifest Answers\n\nManifest answers these questions about your OpenClaw agents — via the dashboard or directly in-conversation via agent tools:\n\n**Spending & budget**\n\n- How much have I spent today \u002F this week \u002F this month?\n- What's my cost breakdown by model?\n- Which model consumes the biggest share of my budget?\n- Am I approaching my spending limit?\n\n**Token consumption**\n\n- How many tokens has my agent used (input vs. output)?\n- What's my token trend compared to the previous period?\n- How much cache am I reading vs. writing?\n\n**Activity & performance**\n\n- How many LLM calls has my agent made?\n- How long do LLM calls take (latency)?\n- Are there errors or rate limits occurring? What are the error messages?\n- Which skills\u002Ftools are running and how often?\n\n**Routing intelligence**\n\n- What routing tier (simple\u002Fstandard\u002Fcomplex\u002Freasoning) was each request assigned?\n- Why was a specific tier chosen?\n- What model pricing is available across all providers?\n\n**Connectivity**\n\n- Is Manifest connected and healthy?\n- Is telemetry flowing correctly?\n\n## Agent Tools\n\nThree tools are available to the agent in-conversation:\n\n| Tool              | Trigger phrases                                 | What it returns                                                             |\n| ----------------- | ----------------------------------------------- | --------------------------------------------------------------------------- |\n| `manifest_usage`  | \"how many tokens\", \"token usage\", \"consumption\" | Total, input, output, cache-read tokens + action count for today\u002Fweek\u002Fmonth |\n| `manifest_costs`  | \"how much spent\", \"costs\", \"money burned\"       | Cost breakdown by model in USD for today\u002Fweek\u002Fmonth                         |\n| `manifest_health` | \"is monitoring working\", \"connectivity test\"    | Endpoint reachable, auth valid, agent name, status                          |\n\nEach accepts a `period` parameter: `\"today\"`, `\"week\"`, or `\"month\"`.\n\nAll three tools are read-only — they query the agent's own usage data and never send message content.\n\n## LLM Routing\n\nWhen the model is set to `manifest\u002Fauto`, the router scores each conversation across 23 dimensions and assigns one of 4 tiers:\n\n| Tier          | Use case                                | Examples                                                |\n| ------------- | --------------------------------------- | ------------------------------------------------------- |\n| **Simple**    | Greetings, confirmations, short lookups | \"hi\", \"yes\", \"what time is it\"                          |\n| **Standard**  | General tasks, balanced quality\u002Fcost    | \"summarize this\", \"write a test\"                        |\n| **Complex**   | Multi-step reasoning, nuanced analysis  | \"compare these architectures\", \"debug this stack trace\" |\n| **Reasoning** | Formal logic, proofs, critical planning | \"prove this theorem\", \"design a migration strategy\"     |\n\nEach tier maps to a model. Default models are auto-assigned per provider, but overridable in the dashboard under **Routing**.\n\nShort-circuit rules:\n\n- Messages \u003C50 chars with no tools → **Simple**\n- Formal logic keywords → **Reasoning**\n- Tools present → floor at **Standard**\n- Context >50k tokens → floor at **Complex**\n\n## Dashboard Pages\n\n| Page             | What it shows                                                                 |\n| ---------------- | ----------------------------------------------------------------------------- |\n| **Workspace**    | All connected agents as cards with sparkline activity charts                  |\n| **Overview**     | Per-agent cost, tokens, messages with trend badges and time-series charts     |\n| **Messages**     | Full paginated message log with filters (status, model, cost range)           |\n| **Routing**      | 4-tier model config, provider connections, enable\u002Fdisable routing             |\n| **Limits**       | Email alerts and hard spending caps (tokens or cost, per hour\u002Fday\u002Fweek\u002Fmonth) |\n| **Settings**     | Agent rename, delete, OTLP key management                                     |\n| **Model Prices** | Sortable table of 300+ model prices across all providers                      |\n\n## Supported Providers\n\nAnthropic, OpenAI, Google Gemini, DeepSeek, xAI, Mistral AI, Qwen, MiniMax, Kimi, Amazon Nova, Z.ai, OpenRouter, Ollama. 300+ models total.\n\n## Uninstall\n\n```bash\nopenclaw plugins uninstall manifest\nopenclaw gateway restart\n```\n\nThis removes the plugin, provider config, and auth profiles. After uninstalling, `manifest\u002Fauto` is no longer available. If any agent uses it, switch to another model.\n\n## Troubleshooting\n\n**Telemetry not appearing**: The gateway batches OTLP data every 10-30 seconds. Wait, then check `openclaw manifest` for connection status.\n\n**Auth errors in cloud mode**: Verify the API key starts with `mnfst_` and matches the key in the dashboard under Settings → Agent setup.\n\n**Port conflict in local mode**: If port 2099 is busy, the plugin checks if the existing process is Manifest and reuses it. To change the port: `openclaw config set plugins.entries.manifest.config.port \u003CPORT>`.\n\n**Plugin conflicts**: Manifest conflicts with the built-in `diagnostics-otel` plugin. Disable it before enabling Manifest.\n\n**After backend restart**: Always restart the gateway too (`openclaw gateway restart`) — the OTLP pipeline doesn't auto-reconnect.\n\n## Privacy\n\n### External Endpoints\n\n| Endpoint                            | When                               | Data Sent                                                                                                 |\n| ----------------------------------- | ---------------------------------- | --------------------------------------------------------------------------------------------------------- |\n| `{endpoint}\u002Fv1\u002Ftraces`              | Every LLM call (batched 10-30s)    | OTLP spans (see fields below)                                                                             |\n| `{endpoint}\u002Fv1\u002Fmetrics`             | Every 10-30s                       | Counters: request count, token totals, tool call counts — grouped by model\u002Fprovider                       |\n| `{endpoint}\u002Fapi\u002Fv1\u002Frouting\u002Fresolve` | Only when model is `manifest\u002Fauto` | Last 10 non-system\u002Fnon-developer messages (`{role, content}` only)                                        |\n| `https:\u002F\u002Feu.i.posthog.com`          | On plugin register                 | Hashed machine ID, OS, Node version, plugin version, mode. No PII. Opt out: `MANIFEST_TELEMETRY_OPTOUT=1` |\n\n### OTLP Span Fields\n\nExhaustive list of attributes sent per span:\n\n- `openclaw.session.key` — opaque session identifier\n- `openclaw.message.channel` — message channel name\n- `gen_ai.request.model` — model name (e.g. \"claude-sonnet-4-20250514\")\n- `gen_ai.system` — provider name (e.g. \"anthropic\")\n- `gen_ai.usage.input_tokens` — integer\n- `gen_ai.usage.output_tokens` — integer\n- `gen_ai.usage.cache_read_input_tokens` — integer\n- `gen_ai.usage.cache_creation_input_tokens` — integer\n- `openclaw.agent.name` — agent identifier\n- `tool.name` — tool name string\n- `tool.success` — boolean\n- `manifest.routing.tier` — routing tier (if routed)\n- `manifest.routing.reason` — routing reason (if routed)\n- Error status: agent errors truncated to 500 chars; tool errors include `event.error.message` untruncated\n\n**Not collected**: user prompts, assistant responses, tool input\u002Foutput arguments, file contents, or any message body.\n\n### Routing Data\n\n- Only active when model is `manifest\u002Fauto`\n- Excludes messages with `role: \"system\"` or `role: \"developer\"`\n- Sends only `{role, content}` — all other message properties are stripped (`routing.ts:77`)\n- 3-second timeout, non-blocking\n- To avoid sending content: disable routing in the dashboard or set a fixed model\n\n### Credential Storage\n\n- **Cloud mode**: API key stored in `~\u002F.openclaw\u002Fopenclaw.json` under `plugins.entries.manifest.config.apiKey` (managed by OpenClaw's standard plugin config)\n- **Local mode**: auto-generated key stored in `~\u002F.openclaw\u002Fmanifest\u002Fconfig.json` with file mode `0600`\n\n### Local Mode\n\nAll data stays on your machine. No external calls except optional PostHog analytics (opt out with `MANIFEST_TELEMETRY_OPTOUT=1`).\n",{"name":5,"metadata":24,"description":7},{"openclaw":25},{"homepage":26,"requires":27,"primaryEnv":29},"https:\u002F\u002Fgithub.com\u002Fmnfst\u002Fmanifest",{"env":28,"bins":30,"config":32},[29],"MANIFEST_API_KEY",[31],"openclaw",[33],"plugins.entries.manifest.config.apiKey","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fbrunobuddy\u002Fmanifest-build",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill manifest",{"tool":49,"command":50},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill manifest",{"tool":52,"command":53},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill manifest","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbrunobuddy\u002Fmanifest-build\u002FSKILL.md",true,[],[58,66,73,80,87,94],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":65},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":65},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":65},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":65},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":65},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":65},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]