[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BV316C5R2CNN5ZJ8VDAM77":3,"skill-same:01M7BV316C5R2CNN5ZJ8VDAM77":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7BV316C5R2CNN5ZJ8VDAM77","caveman-setup",null,"Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for \"set up caveman\" or adding LLM spend observability.","nguyenhungtran18\u002Fskill-and-tool-tracker","nguyenhungtran18","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F297063550?v=4","01M7BV0BFPRRFP84F2ME0FYZ9D","01M7BV0BG83FA5P22NJV0GR0A5",1,"MIT","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fcaveman-setup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: caveman-setup\ndescription: >\n  Wire a repository through the Caveman Cloud gateway so every LLM request is\n  measured, with no behavior change. Use for \"set up caveman\" or adding LLM\n  spend observability.\n---\n\nYou are wiring this repository through the Caveman gateway. Caveman is a\nbyte-preserving LLM proxy: in record mode it measures what your app sends and\nwhat it costs, and changes nothing else. Your job is a minimal, verified\nintegration — not a refactor.\n\nThe prompt that sent you here provides four values. Refer to them as:\n\n- `GATEWAY` — the gateway base URL (e.g. `https:\u002F\u002Fgateway.caveman.so` or `http:\u002F\u002F127.0.0.1:8787`)\n- `CAVE_API_KEY` — the gateway auth secret (treat like any API key: env var only, never committed, never printed in full)\n- `PROVIDER_KEYS` — `stored` (provider keys live encrypted in Caveman Cloud) or `byok` (this app sends its own provider key per request)\n- `DASHBOARD` — the dashboard base URL (e.g. `https:\u002F\u002Fapp.caveman.so`)\n\nIf any value is missing, stop and ask for it. Do not guess a URL or mint a key.\n\n## Rules (non-negotiable)\n\n1. **Coherent integration.** Wire every live LLM callsite through existing\n   configuration and responsible seams. Touch each layer correctness requires.\n   No drive-by refactors or formatting sweeps; add an abstraction only when it\n   clarifies ownership or lowers lifecycle cost.\n2. **Secrets stay in env vars.** `CAVE_API_KEY` goes into the env file the repo\n   already uses (`.env`, `.env.local`, …). If that file isn't gitignored, add it\n   to `.gitignore` and say so. Never hardcode the key in source.\n3. **Report only what you observed.** The final report states the HTTP status\n   and usage numbers from the real verification response — never assumed\n   success. If verification fails, report the failure template instead.\n4. **Record mode only.** You are adding measurement. You do not enable any\n   optimization, and you do not claim any savings — verified savings are $0\n   until an optimizer is explicitly turned on and passes its eval gate.\n5. **Provider keys are not your business.** With `PROVIDER_KEYS: stored` you\n   never see one. With `byok`, the app's existing provider key stays exactly\n   where it already is.\n\n## Step 1 — Find every live LLM callsite\n\nRead dependency files (`package.json`, `requirements.txt`, `pyproject.toml`,\n`go.mod`, lockfiles) and search the source for LLM clients:\n\n- SDK imports: `openai`, `@anthropic-ai\u002Fsdk`, `anthropic`, `ai` +\n  `@ai-sdk\u002F*` (Vercel), `langchain*`, `litellm`, `google-genai` \u002F\n  `@google\u002Fgenai`, `crewai`, `pydantic_ai`, `openai-agents` \u002F `agents`\n- Raw HTTP to `api.openai.com`, `api.anthropic.com`, `generativelanguage.googleapis.com`\n- Existing base-URL env vars: `OPENAI_BASE_URL`, `OPENAI_API_BASE`,\n  `ANTHROPIC_BASE_URL`, `GEMINI_BASE_URL`, `GOOGLE_GEMINI_BASE_URL`\n\nList what you found (file:line per callsite) before changing anything. If you\nfind **no** LLM callsites, stop and report the \"nothing to wire\" template at\nthe end of this file — do not invent an integration.\n\n## Step 2 — Pick the app slug\n\nOne slug names this app in the gateway path: `GATEWAY\u002Fw\u002F\u003Capp>`. Derive it from\nthe package\u002Fmodule name (e.g. `support-bot`, `acme-api`). Grammar:\nlowercase `[a-z0-9]` first, then `[a-z0-9._-]`, max 64 chars. Spend for this\nwhole app groups under that slug on the dashboard.\n\n## Step 3 — Wire each callsite\n\nThe pattern is always the same: **base URL → the gateway with `\u002Fw\u002F\u003Capp>`,\nplus one auth header.** Gateway auth is `x-cave-api-key: CAVE_API_KEY`\n(`Authorization: Bearer CAVE_API_KEY` also works where a header is awkward).\nWith `PROVIDER_KEYS: byok`, also send `x-cave-upstream-key: \u003Cthe provider key\nthe app already uses>`.\n\nTwo facts that make the wiring safe (both are gateway-enforced, not hopes):\nthe gateway rebuilds upstream auth headers from scratch, so a client's\n`Authorization`\u002F`x-api-key` value is never forwarded to the provider; and with\n`stored`, upstream auth comes from the encrypted connection server-side. So in\n`stored` mode, where an SDK insists on an api-key parameter, set it to the\nCave key — it authenticates the gateway and goes no further.\n\nExact shapes (use the one matching each callsite — these are the product's\npublished recipes, not suggestions):\n\n**OpenAI SDK (TS)** — Chat Completions and Responses both route through:\n```ts\nconst client = new OpenAI({\n  baseURL: `${process.env.CAVE_GATEWAY_URL}\u002Fw\u002F\u003Capp>\u002Fopenai\u002Fv1`,\n  apiKey: process.env.OPENAI_API_KEY,           \u002F\u002F byok: unchanged · stored: use CAVE_API_KEY\n  defaultHeaders: {\n    \"x-cave-api-key\": process.env.CAVE_API_KEY!,\n    \u002F\u002F byok only:\n    \"x-cave-upstream-key\": process.env.OPENAI_API_KEY!,\n  },\n});\n```\n\n**OpenAI SDK (Python)** — same shape: `base_url=f\"{gw}\u002Fw\u002F\u003Capp>\u002Fopenai\u002Fv1\"`,\n`default_headers={\"x-cave-api-key\": ..., \"x-cave-upstream-key\": ...}`.\n\n**Anthropic SDK (TS\u002FPython)** — the SDK appends `\u002Fv1\u002Fmessages` itself. The\n`x-cave-api-key` header is required here in both modes (this SDK's own key\nparam rides `x-api-key`, which is not a gateway-auth header):\n```python\nclient = anthropic.Anthropic(\n    base_url=f\"{os.environ['CAVE_GATEWAY_URL']}\u002Fw\u002F\u003Capp>\",\n    api_key=os.environ[\"ANTHROPIC_API_KEY\"],      # byok: unchanged · stored: use CAVE_API_KEY\n    default_headers={\n        \"x-cave-api-key\": os.environ[\"CAVE_API_KEY\"],\n        # byok only:\n        \"x-cave-upstream-key\": os.environ[\"ANTHROPIC_API_KEY\"],\n    },\n)\n```\n\n**Vercel AI SDK** — `createOpenAICompatible({ baseURL: `${gw}\u002Fw\u002F\u003Capp>\u002Fopenai\u002Fv1`,\nheaders: { \"x-cave-api-key\": ... } })`; Anthropic models via\n`createAnthropic({ baseURL: `${gw}\u002Fw\u002F\u003Capp>\u002Fv1`, headers: { ... } })`.\n\n**LangChain \u002F LangGraph** — `ChatOpenAI(base_url=f\"{gw}\u002Fw\u002F\u003Capp>\u002Fopenai\u002Fv1\",\ndefault_headers={...})`; `ChatAnthropic(base_url=f\"{gw}\u002Fw\u002F\u003Capp>\",\ndefault_headers={...})`. LangGraph inherits whatever model you pass it.\n\n**LiteLLM** — per call `api_base=f\"{gw}\u002Fw\u002F\u003Capp>\u002Fopenai\u002Fv1\"` +\n`extra_headers={...}`, or fleet-wide in the LiteLLM proxy `config.yaml`.\n\n**Raw HTTP \u002F anything else** — swap the host, keep the provider's native path:\n`GATEWAY\u002Fw\u002F\u003Capp>\u002Fv1\u002Fchat\u002Fcompletions` (OpenAI protocol) or\n`GATEWAY\u002Fw\u002F\u003Capp>\u002Fv1\u002Fmessages` (Anthropic protocol), add the header(s).\n\nConcretely, with slug `support-bot` and the hosted gateway, an OpenAI-SDK base\nURL reads `https:\u002F\u002Fgateway.caveman.so\u002Fw\u002Fsupport-bot\u002Fopenai\u002Fv1`. And in `stored`\nmode, drop every `x-cave-upstream-key` line entirely — it is byok-only.\n\nFor frameworks not listed (google-genai, crewai, pydantic-ai, openai-agents),\nfetch the matching page under `\u003Cdocs origin>\u002Fdocs\u002Fintegrations\u002F` — same origin\nthis skill came from — and follow it.\n\nAdd to the repo's env file (and reference from code — no literals):\n\n```\nCAVE_GATEWAY_URL=\u003CGATEWAY>\nCAVE_API_KEY=\u003CCAVE_API_KEY>\n```\n\n## Step 4 — Verify with one real request\n\nThe user pasted the setup prompt to authorize exactly this: one small\nverification request. Send it now — do not pause to ask permission for it.\nAn integration that ends unverified because you hesitated is a worse outcome\nthan one tiny request; finishing the verification and the report autonomously\nis the point of this skill.\n\nSend one minimal request through the wiring you just built — the app's own\ncheapest path if it has a script for it, otherwise curl **on the path matching\nthe protocol you just wired** with the app's own model and a small cap\n(`max_tokens` ≤ 32):\n\n```bash\n# OpenAI-protocol wiring:\ncurl -sS \"$CAVE_GATEWAY_URL\u002Fw\u002F\u003Capp>\u002Fv1\u002Fchat\u002Fcompletions\" \\\n  -H \"x-cave-api-key: $CAVE_API_KEY\" \\\n  -H \"content-type: application\u002Fjson\" \\\n  -d '{\"model\":\"\u003Cmodel the repo already uses>\",\"max_tokens\":16,\"messages\":[{\"role\":\"user\",\"content\":\"ping\"}]}'\n\n# Anthropic-protocol wiring:\ncurl -sS \"$CAVE_GATEWAY_URL\u002Fw\u002F\u003Capp>\u002Fv1\u002Fmessages\" \\\n  -H \"x-cave-api-key: $CAVE_API_KEY\" \\\n  -H \"anthropic-version: 2023-06-01\" \\\n  -H \"content-type: application\u002Fjson\" \\\n  -d '{\"model\":\"\u003Cmodel the repo already uses>\",\"max_tokens\":16,\"messages\":[{\"role\":\"user\",\"content\":\"ping\"}]}'\n```\n\n(byok: add `-H \"x-cave-upstream-key: $PROVIDER_KEY\"`.) This is one real,\nbillable provider request — that is the point: real traffic, real measurement.\n\nRead the response. Success = HTTP 200 with a `usage` block. Anything else =\nthe matching failure template below.\n\n## Step 5 — Report\n\nEnd with exactly this shape, values filled from what you actually did and saw:\n\n```\n## Caveman is live in this repo\n\nWired: \u003Cn> callsite(s) in \u003Cn> file(s)\n  - \u003Cfile> — \u003Cone-line what changed>\nApp slug: \u003Capp> — spend for this app groups under it\nVerified: HTTP 200 · model \u003Cmodel> · \u003Cin> in \u002F \u003Cout> out tokens (one real request)\nMode: record — measured only. No model-visible bytes changed, no optimization\nenabled. Verified savings are $0 until you turn an optimizer on and it passes\nits eval gate. That honesty is the product.\n\nSee the dollars: \u003CDASHBOARD>\u002Ftraces — your request is the top row, priced from\nthe public catalog. \u003CDASHBOARD>\u002Fgetting-started flips to \"First request received.\"\n\nWant spend split by workflow (e.g. support-reply vs nightly-digest), not just\nby app? Say \"discover workflows\" — I'll fetch \u003Cdocs origin>\u002Fdocs\u002Fdiscover-workflows.md\nand label every callsite by the job it does.\n```\n\n## Failure templates (use verbatim, filled in — never soften)\n\n- **Nothing to wire**: \"I found no LLM callsites in this repo (searched SDKs,\n  raw provider HTTP, base-URL env vars). If this repo runs a coding agent\n  rather than shipping LLM code, use `caveman wrap \u003Cagent>` instead — see\n  \u003CDASHBOARD>\u002Fgetting-started.\"\n- **Gateway unreachable**: \"The verification request could not reach GATEWAY\n  (\u003Cerror>). Wiring is in place but unverified — nothing will be measured\n  until the gateway is reachable. Check the URL and network, then re-run the\n  verification curl above.\"\n- **401 cave_invalid_api_key**: \"The gateway rejected CAVE_API_KEY. Mint a new\n  key at \u003CDASHBOARD>\u002Fgetting-started and update the env file; the wiring\n  itself is unchanged.\"\n- **404 cave_route_not_found**: \"The gateway matched no route — usually a\n  malformed \u002Fw\u002F\u003Capp> slug (lowercase [a-z0-9] first, then [a-z0-9._-], max 64)\n  or a path that doesn't match the SDK's protocol. Fix the URL and re-verify.\"\n- **Provider error (4xx\u002F5xx via gateway)**: report status + body verbatim; the\n  gateway is reachable and auth passed, the upstream call failed — usually a\n  provider key or model-name issue in the app itself.\n\nNever report success on any of these. An unverified integration is reported as\nunverified.\n","You are wiring this repository through the Caveman gateway. Caveman is a\nbyte-preserving LLM proxy: in record mode it measures what your app sends and\nwhat it costs, and changes nothing else. Your job is a minimal, verified\nintegration — not a refactor.\n\nThe prompt that sent you here provides four values. Refer to them as:\n\n- `GATEWAY` — the gateway base URL (e.g. `https:\u002F\u002Fgateway.caveman.so` or `http:\u002F\u002F127.0.0.1:8787`)\n- `CAVE_API_KEY` — the gateway auth secret (treat like any API key: env var only, never committed, never printed in full)\n- `PROVIDER_KEYS` — `stored` (provider keys live encrypted in Caveman Cloud) or `byok` (this app sends its own provider key per request)\n- `DASHBOARD` — the dashboard base URL (e.g. `https:\u002F\u002Fapp.caveman.so`)\n\nIf any value is missing, stop and ask for it. Do not guess a URL or mint a key.\n\n## Rules (non-negotiable)\n\n1. **Coherent integration.** Wire every live LLM callsite through existing\n   configuration and responsible seams. Touch each layer correctness requires.\n   No drive-by refactors or formatting sweeps; add an abstraction only when it\n   clarifies ownership or lowers lifecycle cost.\n2. **Secrets stay in env vars.** `CAVE_API_KEY` goes into the env file the repo\n   already uses (`.env`, `.env.local`, …). If that file isn't gitignored, add it\n   to `.gitignore` and say so. Never hardcode the key in source.\n3. **Report only what you observed.** The final report states the HTTP status\n   and usage numbers from the real verification response — never assumed\n   success. If verification fails, report the failure template instead.\n4. **Record mode only.** You are adding measurement. You do not enable any\n   optimization, and you do not claim any savings — verified savings are $0\n   until an optimizer is explicitly turned on and passes its eval gate.\n5. **Provider keys are not your business.** With `PROVIDER_KEYS: stored` you\n   never see one. With `byok`, the app's existing provider key stays exactly\n   where it already is.\n\n## Step 1 — Find every live LLM callsite\n\nRead dependency files (`package.json`, `requirements.txt`, `pyproject.toml`,\n`go.mod`, lockfiles) and search the source for LLM clients:\n\n- SDK imports: `openai`, `@anthropic-ai\u002Fsdk`, `anthropic`, `ai` +\n  `@ai-sdk\u002F*` (Vercel), `langchain*`, `litellm`, `google-genai` \u002F\n  `@google\u002Fgenai`, `crewai`, `pydantic_ai`, `openai-agents` \u002F `agents`\n- Raw HTTP to `api.openai.com`, `api.anthropic.com`, `generativelanguage.googleapis.com`\n- Existing base-URL env vars: `OPENAI_BASE_URL`, `OPENAI_API_BASE`,\n  `ANTHROPIC_BASE_URL`, `GEMINI_BASE_URL`, `GOOGLE_GEMINI_BASE_URL`\n\nList what you found (file:line per callsite) before changing anything. If you\nfind **no** LLM callsites, stop and report the \"nothing to wire\" template at\nthe end of this file — do not invent an integration.\n\n## Step 2 — Pick the app slug\n\nOne slug names this app in the gateway path: `GATEWAY\u002Fw\u002F\u003Capp>`. Derive it from\nthe package\u002Fmodule name (e.g. `support-bot`, `acme-api`). Grammar:\nlowercase `[a-z0-9]` first, then `[a-z0-9._-]`, max 64 chars. Spend for this\nwhole app groups under that slug on the dashboard.\n\n## Step 3 — Wire each callsite\n\nThe pattern is always the same: **base URL → the gateway with `\u002Fw\u002F\u003Capp>`,\nplus one auth header.** Gateway auth is `x-cave-api-key: CAVE_API_KEY`\n(`Authorization: Bearer CAVE_API_KEY` also works where a header is awkward).\nWith `PROVIDER_KEYS: byok`, also send `x-cave-upstream-key: \u003Cthe provider key\nthe app already uses>`.\n\nTwo facts that make the wiring safe (both are gateway-enforced, not hopes):\nthe gateway rebuilds upstream auth headers from scratch, so a client's\n`Authorization`\u002F`x-api-key` value is never forwarded to the provider; and with\n`stored`, upstream auth comes from the encrypted connection server-side. So in\n`stored` mode, where an SDK insists on an api-key parameter, set it to the\nCave key — it authenticates the gateway and goes no further.\n\nExact shapes (use the one matching each callsite — these are the product's\npublished recipes, not suggestions):\n\n**OpenAI SDK (TS)** — Chat Completions and Responses both route through:\n```ts\nconst client = new OpenAI({\n  baseURL: `${process.env.CAVE_GATEWAY_URL}\u002Fw\u002F\u003Capp>\u002Fopenai\u002Fv1`,\n  apiKey: process.env.OPENAI_API_KEY,           \u002F\u002F byok: unchanged · stored: use CAVE_API_KEY\n  defaultHeaders: {\n    \"x-cave-api-key\": process.env.CAVE_API_KEY!,\n    \u002F\u002F byok only:\n    \"x-cave-upstream-key\": process.env.OPENAI_API_KEY!,\n  },\n});\n```\n\n**OpenAI SDK (Python)** — same shape: `base_url=f\"{gw}\u002Fw\u002F\u003Capp>\u002Fopenai\u002Fv1\"`,\n`default_headers={\"x-cave-api-key\": ..., \"x-cave-upstream-key\": ...}`.\n\n**Anthropic SDK (TS\u002FPython)** — the SDK appends `\u002Fv1\u002Fmessages` itself. The\n`x-cave-api-key` header is required here in both modes (this SDK's own key\nparam rides `x-api-key`, which is not a gateway-auth header):\n```python\nclient = anthropic.Anthropic(\n    base_url=f\"{os.environ['CAVE_GATEWAY_URL']}\u002Fw\u002F\u003Capp>\",\n    api_key=os.environ[\"ANTHROPIC_API_KEY\"],      # byok: unchanged · stored: use CAVE_API_KEY\n    default_headers={\n        \"x-cave-api-key\": os.environ[\"CAVE_API_KEY\"],\n        # byok only:\n        \"x-cave-upstream-key\": os.environ[\"ANTHROPIC_API_KEY\"],\n    },\n)\n```\n\n**Vercel AI SDK** — `createOpenAICompatible({ baseURL: `${gw}\u002Fw\u002F\u003Capp>\u002Fopenai\u002Fv1`,\nheaders: { \"x-cave-api-key\": ... } })`; Anthropic models via\n`createAnthropic({ baseURL: `${gw}\u002Fw\u002F\u003Capp>\u002Fv1`, headers: { ... } })`.\n\n**LangChain \u002F LangGraph** — `ChatOpenAI(base_url=f\"{gw}\u002Fw\u002F\u003Capp>\u002Fopenai\u002Fv1\",\ndefault_headers={...})`; `ChatAnthropic(base_url=f\"{gw}\u002Fw\u002F\u003Capp>\",\ndefault_headers={...})`. LangGraph inherits whatever model you pass it.\n\n**LiteLLM** — per call `api_base=f\"{gw}\u002Fw\u002F\u003Capp>\u002Fopenai\u002Fv1\"` +\n`extra_headers={...}`, or fleet-wide in the LiteLLM proxy `config.yaml`.\n\n**Raw HTTP \u002F anything else** — swap the host, keep the provider's native path:\n`GATEWAY\u002Fw\u002F\u003Capp>\u002Fv1\u002Fchat\u002Fcompletions` (OpenAI protocol) or\n`GATEWAY\u002Fw\u002F\u003Capp>\u002Fv1\u002Fmessages` (Anthropic protocol), add the header(s).\n\nConcretely, with slug `support-bot` and the hosted gateway, an OpenAI-SDK base\nURL reads `https:\u002F\u002Fgateway.caveman.so\u002Fw\u002Fsupport-bot\u002Fopenai\u002Fv1`. And in `stored`\nmode, drop every `x-cave-upstream-key` line entirely — it is byok-only.\n\nFor frameworks not listed (google-genai, crewai, pydantic-ai, openai-agents),\nfetch the matching page under `\u003Cdocs origin>\u002Fdocs\u002Fintegrations\u002F` — same origin\nthis skill came from — and follow it.\n\nAdd to the repo's env file (and reference from code — no literals):\n\n```\nCAVE_GATEWAY_URL=\u003CGATEWAY>\nCAVE_API_KEY=\u003CCAVE_API_KEY>\n```\n\n## Step 4 — Verify with one real request\n\nThe user pasted the setup prompt to authorize exactly this: one small\nverification request. Send it now — do not pause to ask permission for it.\nAn integration that ends unverified because you hesitated is a worse outcome\nthan one tiny request; finishing the verification and the report autonomously\nis the point of this skill.\n\nSend one minimal request through the wiring you just built — the app's own\ncheapest path if it has a script for it, otherwise curl **on the path matching\nthe protocol you just wired** with the app's own model and a small cap\n(`max_tokens` ≤ 32):\n\n```bash\n# OpenAI-protocol wiring:\ncurl -sS \"$CAVE_GATEWAY_URL\u002Fw\u002F\u003Capp>\u002Fv1\u002Fchat\u002Fcompletions\" \\\n  -H \"x-cave-api-key: $CAVE_API_KEY\" \\\n  -H \"content-type: application\u002Fjson\" \\\n  -d '{\"model\":\"\u003Cmodel the repo already uses>\",\"max_tokens\":16,\"messages\":[{\"role\":\"user\",\"content\":\"ping\"}]}'\n\n# Anthropic-protocol wiring:\ncurl -sS \"$CAVE_GATEWAY_URL\u002Fw\u002F\u003Capp>\u002Fv1\u002Fmessages\" \\\n  -H \"x-cave-api-key: $CAVE_API_KEY\" \\\n  -H \"anthropic-version: 2023-06-01\" \\\n  -H \"content-type: application\u002Fjson\" \\\n  -d '{\"model\":\"\u003Cmodel the repo already uses>\",\"max_tokens\":16,\"messages\":[{\"role\":\"user\",\"content\":\"ping\"}]}'\n```\n\n(byok: add `-H \"x-cave-upstream-key: $PROVIDER_KEY\"`.) This is one real,\nbillable provider request — that is the point: real traffic, real measurement.\n\nRead the response. Success = HTTP 200 with a `usage` block. Anything else =\nthe matching failure template below.\n\n## Step 5 — Report\n\nEnd with exactly this shape, values filled from what you actually did and saw:\n\n```\n## Caveman is live in this repo\n\nWired: \u003Cn> callsite(s) in \u003Cn> file(s)\n  - \u003Cfile> — \u003Cone-line what changed>\nApp slug: \u003Capp> — spend for this app groups under it\nVerified: HTTP 200 · model \u003Cmodel> · \u003Cin> in \u002F \u003Cout> out tokens (one real request)\nMode: record — measured only. No model-visible bytes changed, no optimization\nenabled. Verified savings are $0 until you turn an optimizer on and it passes\nits eval gate. That honesty is the product.\n\nSee the dollars: \u003CDASHBOARD>\u002Ftraces — your request is the top row, priced from\nthe public catalog. \u003CDASHBOARD>\u002Fgetting-started flips to \"First request received.\"\n\nWant spend split by workflow (e.g. support-reply vs nightly-digest), not just\nby app? Say \"discover workflows\" — I'll fetch \u003Cdocs origin>\u002Fdocs\u002Fdiscover-workflows.md\nand label every callsite by the job it does.\n```\n\n## Failure templates (use verbatim, filled in — never soften)\n\n- **Nothing to wire**: \"I found no LLM callsites in this repo (searched SDKs,\n  raw provider HTTP, base-URL env vars). If this repo runs a coding agent\n  rather than shipping LLM code, use `caveman wrap \u003Cagent>` instead — see\n  \u003CDASHBOARD>\u002Fgetting-started.\"\n- **Gateway unreachable**: \"The verification request could not reach GATEWAY\n  (\u003Cerror>). Wiring is in place but unverified — nothing will be measured\n  until the gateway is reachable. Check the URL and network, then re-run the\n  verification curl above.\"\n- **401 cave_invalid_api_key**: \"The gateway rejected CAVE_API_KEY. Mint a new\n  key at \u003CDASHBOARD>\u002Fgetting-started and update the env file; the wiring\n  itself is unchanged.\"\n- **404 cave_route_not_found**: \"The gateway matched no route — usually a\n  malformed \u002Fw\u002F\u003Capp> slug (lowercase [a-z0-9] first, then [a-z0-9._-], max 64)\n  or a path that doesn't match the SDK's protocol. Fix the URL and re-verify.\"\n- **Provider error (4xx\u002F5xx via gateway)**: report status + body verbatim; the\n  gateway is reachable and auth passed, the upstream call failed — usually a\n  provider key or model-name issue in the app itself.\n\nNever report success on any of these. An unverified integration is reported as\nunverified.\n",{"name":5,"description":7},"main","900ea3c9eb045fd5b0317dc1103777ecf3ea4aeb","skills\u002Fcaveman-setup",0,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker","https:\u002F\u002Fnguyenhungtran18.github.io\u002Fskill-and-tool-tracker\u002F","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18","2026-08-31 18:36:09",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add nguyenhungtran18\u002Fskill-and-tool-tracker --skill caveman-setup",{"tool":37,"command":38},"bunx","bunx skills add nguyenhungtran18\u002Fskill-and-tool-tracker --skill caveman-setup",{"tool":40,"command":41},"pnpm","pnpm dlx skills add nguyenhungtran18\u002Fskill-and-tool-tracker --skill caveman-setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fcaveman-setup\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M7BVP4P83TK60JZ4P8RP9VP7","xcode-project-setup","Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fxcode_project_setup\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M7BVP01K4CSJJ8G90FT8S2D5","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M7BVNY22GXD871GYTSH599F1","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7BVNQWF24RNKA8A4KM2HJ3T","workflow-skill-creator","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7BVNNY67XPCQAQHY3FBKDGC","verify-and-stop","Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fverify-and-stop\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M7BVNKB4Z7SZT85B73ZZ90Y6","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[]]