[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M758ACVC35DYYZQJAR1W4H9A":3,"skill-same:01M758ACVC35DYYZQJAR1W4H9A":63},{"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":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M758ACVC35DYYZQJAR1W4H9A","kanban-worker",null,"Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent\u002Fprompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.","lukemcqueen\u002Fsteadfaste-fleet","lukemcqueen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F405240?v=4","01M757MHPAGRXTJAT46SKZP98R","Luke McQueen","01M757MHPZ573KP8DT9GB8SBQ7",4,"MIT","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fkanban-worker\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: kanban-worker\ndescription: Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent\u002Fprompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.\nversion: 2.0.0\nplatforms: [linux, macos, windows]\nenvironments: [kanban]\nmetadata:\n  hermes:\n    tags: [kanban, multi-agent, collaboration, workflow, pitfalls]\n    related_skills: [kanban-orchestrator]\n---\n\n# Kanban Worker — Pitfalls and Examples\n\n> You're seeing this skill because the Hermes Kanban dispatcher spawned you as a worker with `--skills kanban-worker` — it's loaded automatically for every dispatched worker. The **lifecycle** (6 steps: orient → work → heartbeat → block\u002Fcomplete) also lives in the `KANBAN_GUIDANCE` block that's auto-injected into your system prompt. This skill is the deeper detail: good handoff shapes, retry diagnostics, edge cases.\n\n## Workspace handling\n\nYour workspace kind determines how you should behave inside `$HERMES_KANBAN_WORKSPACE`:\n\n| Kind | What it is | How to work |\n|---|---|---|\n| `scratch` | Fresh tmp dir, yours alone | Read\u002Fwrite freely; it gets GC'd when the task is archived. |\n| `dir:\u003Cpath>` | Shared persistent directory | Other runs will read what you write. Treat it like long-lived state. Path is guaranteed absolute (the kernel rejects relative paths). |\n| `worktree` | Git worktree at the resolved path | If `.git` doesn't exist, run `git worktree add \u003Cpath> ${HERMES_KANBAN_BRANCH:-wt\u002F$HERMES_KANBAN_TASK}` from the main repo first, then cd and work normally. Commit work here. |\n\n## Tenant isolation\n\nIf `$HERMES_TENANT` is set, the task belongs to a tenant namespace. When reading or writing persistent memory, prefix memory entries with the tenant so context doesn't leak across tenants:\n\n- Good: `business-a: Acme is our biggest customer`\n- Bad (leaks): `Acme is our biggest customer`\n\n## Good summary + metadata shapes\n\nThe `kanban_complete(summary=..., metadata=...)` handoff is how downstream workers read what you did. Patterns that work:\n\n**Coding task:**\n```python\nkanban_complete(\n    summary=\"shipped rate limiter — token bucket, keys on user_id with IP fallback, 14 tests pass\",\n    metadata={\n        \"changed_files\": [\"rate_limiter.py\", \"tests\u002Ftest_rate_limiter.py\"],\n        \"tests_run\": 14,\n        \"tests_passed\": 14,\n        \"decisions\": [\"user_id primary, IP fallback for unauthenticated requests\"],\n    },\n)\n```\n\n**Coding task that needs human review (review-required):**\n\nFor most code-changing tasks, the work isn't truly *done* until a human reviewer has eyes on it. Block instead of complete, with `reason` prefixed `review-required: ` so the dashboard surfaces the row as needing review. Drop the structured metadata (changed files, test counts, diff\u002FPR url) into a comment first, since `kanban_block` only carries the human-readable reason — comments are the durable annotation channel. Reviewer either approves and runs `hermes kanban unblock \u003Cid>` (which re-spawns you with the comment thread for any follow-ups) or asks for changes via another comment.\n\n```python\nimport json\n\nkanban_comment(\n    body=\"review-required handoff:\\n\" + json.dumps({\n        \"changed_files\": [\"rate_limiter.py\", \"tests\u002Ftest_rate_limiter.py\"],\n        \"tests_run\": 14,\n        \"tests_passed\": 14,\n        \"diff_path\": \"\u002Fpath\u002Fto\u002Fworktree\",  # or PR url if pushed\n        \"decisions\": [\"user_id primary, IP fallback for unauthenticated requests\"],\n    }, indent=2),\n)\nkanban_block(\n    reason=\"review-required: rate limiter shipped, 14\u002F14 tests pass — needs eyes on the user_id\u002FIP fallback choice before merging\",\n)\n```\n\nUse `kanban_complete` only when the task is genuinely terminal — e.g. a one-line typo fix, a docs change with no functional consequences, or a research task where the artifact IS the writeup itself.\n\n**Research task:**\n```python\nkanban_complete(\n    summary=\"3 competing libraries reviewed; vLLM wins on throughput, SGLang on latency, Tensorrt-LLM on memory efficiency\",\n    metadata={\n        \"sources_read\": 12,\n        \"recommendation\": \"vLLM\",\n        \"benchmarks\": {\"vllm\": 1.0, \"sglang\": 0.87, \"trtllm\": 0.72},\n    },\n)\n```\n\n**Review task:**\n```python\nkanban_complete(\n    summary=\"reviewed PR #123; 2 blocking issues found (SQL injection in \u002Fsearch, missing CSRF on \u002Fsettings)\",\n    metadata={\n        \"pr_number\": 123,\n        \"findings\": [\n            {\"severity\": \"critical\", \"file\": \"api\u002Fsearch.py\", \"line\": 42, \"issue\": \"raw SQL concat\"},\n            {\"severity\": \"high\", \"file\": \"api\u002Fsettings.py\", \"issue\": \"missing CSRF middleware\"},\n        ],\n        \"approved\": False,\n    },\n)\n```\n\nShape `metadata` so downstream parsers (reviewers, aggregators, schedulers) can use it without re-reading your prose.\n\n## Shipping deliverables (`artifacts=[...]`)\n\nIf your task produced files a human actually wants — a chart, a PDF, a spreadsheet, a generated image, an archive — pass their **absolute paths** to `kanban_complete(artifacts=[...])`. The gateway notifier uploads each one as a native attachment to whoever subscribed to the task, so the deliverable lands in their chat alongside the completion message instead of being a path they have to go fetch.\n\n```python\nkanban_complete(\n    summary=\"Q3 revenue analysis: 14% QoQ growth, EMEA the laggard. Chart + full PDF attached.\",\n    artifacts=[\"\u002Ftmp\u002Fq3-revenue.png\", \"\u002Ftmp\u002Fq3-report.pdf\"],\n    metadata={\"rows_analyzed\": 48000, \"growth_qoq\": 0.14},\n)\n```\n\nImages and video embed inline; PDFs, docx, csv\u002Fxlsx\u002Fjson\u002Fyaml, pptx, zip\u002Ftar\u002Fgz, audio, and html upload as files. Rules:\n\n- **Absolute paths only**, and the file must still exist when you complete — don't point at a scratch file you already deleted.\n- **Only real deliverables.** Skip intermediate logs, scratch files, and inputs the human already has.\n- `artifacts` is the **top-level** parameter the notifier reads. Do not bury deliverable paths in `metadata` (e.g. `metadata.codex_lane.artifacts`) and expect them to upload — the notifier only scans the top-level `artifacts` list, with a best-effort fallback over your `summary`\u002F`result` text. Metadata paths are for downstream-worker bookkeeping, not delivery.\n- A bare string is auto-promoted to a one-element list, and it merges with any pre-existing `metadata.artifacts` without dupes.\n\nSame primitive works outside kanban: any agent surface delivers a file just by writing its absolute path into the response, and Slack\u002FDiscord\u002FTelegram\u002Fetc. upload it natively — the `artifacts` param is the structured kanban entry point.\n\n## Claiming cards you actually created\n\nIf your run produced new kanban tasks (via `kanban_create`), pass the ids in `created_cards` on `kanban_complete`. The kernel verifies each id exists and was created by your profile; any phantom id blocks the completion with an error listing what went wrong, and the rejected attempt is permanently recorded on the task's event log. **Only list ids you captured from a successful `kanban_create` return value — never invent ids from prose, never paste ids from earlier runs, never claim cards another worker created.**\n\n```python\n# GOOD — capture return values, then claim them.\nc1 = kanban_create(title=\"remediate SQL injection\", assignee=\"security-worker\")\nc2 = kanban_create(title=\"fix CSRF middleware\", assignee=\"web-worker\")\n\nkanban_complete(\n    summary=\"Review done; spawned remediations for both findings.\",\n    metadata={\"pr_number\": 123, \"approved\": False},\n    created_cards=[c1[\"task_id\"], c2[\"task_id\"]],\n)\n```\n\n```python\n# BAD — claiming ids you don't have captured return values for.\nkanban_complete(\n    summary=\"Created remediation cards t_a1b2c3d4, t_deadbeef\",  # hallucinated\n    created_cards=[\"t_a1b2c3d4\", \"t_deadbeef\"],                   # → gate rejects\n)\n```\n\nIf a `kanban_create` call fails (exception, tool_error), the card was NOT created — do not include a phantom id for it. Retry the create, or omit the id and mention the failure in your summary. The prose-scan pass also catches `t_\u003Chex>` references in your free-form summary that don't resolve; these don't block the completion but show up as advisory warnings on the task in the dashboard.\n\n## Block reasons that get answered fast\n\nBad: `\"stuck\"` — the human has no context.\n\nGood: one sentence naming the specific decision you need. Leave longer context as a comment instead.\n\n```python\nkanban_comment(\n    task_id=os.environ[\"HERMES_KANBAN_TASK\"],\n    body=\"Full context: I have user IPs from Cloudflare headers but some users are behind NATs with thousands of peers. Keying on IP alone causes false positives.\",\n)\nkanban_block(reason=\"Rate limit key choice: IP (simple, NAT-unsafe) or user_id (requires auth, skips anonymous endpoints)?\")\n```\n\nThe block message is what appears in the dashboard \u002F gateway notifier. The comment is the deeper context a human reads when they open the task.\n\n## Heartbeats worth sending\n\nGood heartbeats name progress: `\"epoch 12\u002F50, loss 0.31\"`, `\"scanned 1.2M\u002F2.4M rows\"`, `\"uploaded 47\u002F120 videos\"`.\n\nBad heartbeats: `\"still working\"`, empty notes, sub-second intervals. Every few minutes max; skip entirely for tasks under ~2 minutes.\n\n## Retry scenarios\n\nIf you open the task and `kanban_show` returns `runs: [...]` with one or more closed runs, you're a retry. The prior runs' `outcome` \u002F `summary` \u002F `error` tell you what didn't work. Don't repeat that path. Typical retry diagnostics:\n\n- `outcome: \"timed_out\"` — the previous attempt hit `max_runtime_seconds`. You may need to chunk the work or shorten it.\n- `outcome: \"crashed\"` — OOM or segfault. Reduce memory footprint.\n- `outcome: \"spawn_failed\"` + `error: \"...\"` — usually a profile config issue (missing credential, bad PATH). Ask the human via `kanban_block` instead of retrying blindly.\n- `outcome: \"reclaimed\"` + `summary: \"task archived...\"` — operator archived the task out from under the previous run; you probably shouldn't be running at all, check status carefully.\n- `outcome: \"blocked\"` — a previous attempt blocked; the unblock comment should be in the thread by now.\n\n## Notification routing\n\nYou can configure the gateway to receive cross-profile Kanban task notifications by adding `notification_sources` to `~\u002F.hermes\u002Fconfig.yaml`.\n- `notification_sources: ['*']` accepts subscriptions from all profiles.\n- `notification_sources: ['default', 'zilor-ppt']` or `\"default,zilor-ppt\"` restricts subscriptions to specified profiles.\n- Omitting the key keeps the default behavior (profile isolation).\n\n## Do NOT\n\n- Call `delegate_task` as a substitute for `kanban_create`. `delegate_task` is for short reasoning subtasks inside YOUR run; `kanban_create` is for cross-agent handoffs that outlive one API loop.\n- Call `clarify` to ask the human a question. You are running headless — there is no live user to answer. The call will time out (default ~120s) and the task will sit silently in `running` with no signal that it needs input. Use `kanban_comment` (context) + `kanban_block(reason=...)` (decision needed) instead — the task surfaces on the board as blocked, the operator sees it, unblocks with their answer in a comment, and you respawn with the thread.\n- Modify files outside `$HERMES_KANBAN_WORKSPACE` unless the task body says to.\n- Create follow-up tasks assigned to yourself — assign to the right specialist.\n- Complete a task you didn't actually finish. Block it instead.\n\n## Pitfalls\n\n**Task state can change between dispatch and your startup.** Between when the dispatcher claimed and when your process actually booted, the task may have been blocked, reassigned, or archived. Always `kanban_show` first. If it reports `blocked` or `archived`, stop — you shouldn't be running.\n\n**Workspace may have stale artifacts.** Especially `dir:` and `worktree` workspaces can have files from previous runs. Read the comment thread — it usually explains why you're running again and what state the workspace is in.\n\n**Don't rely on the CLI when the guidance is available.** The `kanban_*` tools work across all terminal backends (Docker, Modal, SSH). `hermes kanban \u003Cverb>` from your terminal tool will fail in containerized backends because the CLI isn't installed there. When in doubt, use the tool.\n\n## CLI fallback (for scripting)\n\nEvery tool has a CLI equivalent for human operators and scripts:\n- `kanban_show` ↔ `hermes kanban show \u003Cid> --json`\n- `kanban_complete` ↔ `hermes kanban complete \u003Cid> --summary \"...\" --metadata '{...}'`\n- `kanban_block` ↔ `hermes kanban block \u003Cid> \"reason\"`\n- `kanban_create` ↔ `hermes kanban create \"title\" --assignee \u003Cprofile> [--parent \u003Cid>]`\n- etc.\n\nUse the tools from inside an agent; the CLI exists for the human at the terminal.\n","# Kanban Worker — Pitfalls and Examples\n\n> You're seeing this skill because the Hermes Kanban dispatcher spawned you as a worker with `--skills kanban-worker` — it's loaded automatically for every dispatched worker. The **lifecycle** (6 steps: orient → work → heartbeat → block\u002Fcomplete) also lives in the `KANBAN_GUIDANCE` block that's auto-injected into your system prompt. This skill is the deeper detail: good handoff shapes, retry diagnostics, edge cases.\n\n## Workspace handling\n\nYour workspace kind determines how you should behave inside `$HERMES_KANBAN_WORKSPACE`:\n\n| Kind | What it is | How to work |\n|---|---|---|\n| `scratch` | Fresh tmp dir, yours alone | Read\u002Fwrite freely; it gets GC'd when the task is archived. |\n| `dir:\u003Cpath>` | Shared persistent directory | Other runs will read what you write. Treat it like long-lived state. Path is guaranteed absolute (the kernel rejects relative paths). |\n| `worktree` | Git worktree at the resolved path | If `.git` doesn't exist, run `git worktree add \u003Cpath> ${HERMES_KANBAN_BRANCH:-wt\u002F$HERMES_KANBAN_TASK}` from the main repo first, then cd and work normally. Commit work here. |\n\n## Tenant isolation\n\nIf `$HERMES_TENANT` is set, the task belongs to a tenant namespace. When reading or writing persistent memory, prefix memory entries with the tenant so context doesn't leak across tenants:\n\n- Good: `business-a: Acme is our biggest customer`\n- Bad (leaks): `Acme is our biggest customer`\n\n## Good summary + metadata shapes\n\nThe `kanban_complete(summary=..., metadata=...)` handoff is how downstream workers read what you did. Patterns that work:\n\n**Coding task:**\n```python\nkanban_complete(\n    summary=\"shipped rate limiter — token bucket, keys on user_id with IP fallback, 14 tests pass\",\n    metadata={\n        \"changed_files\": [\"rate_limiter.py\", \"tests\u002Ftest_rate_limiter.py\"],\n        \"tests_run\": 14,\n        \"tests_passed\": 14,\n        \"decisions\": [\"user_id primary, IP fallback for unauthenticated requests\"],\n    },\n)\n```\n\n**Coding task that needs human review (review-required):**\n\nFor most code-changing tasks, the work isn't truly *done* until a human reviewer has eyes on it. Block instead of complete, with `reason` prefixed `review-required: ` so the dashboard surfaces the row as needing review. Drop the structured metadata (changed files, test counts, diff\u002FPR url) into a comment first, since `kanban_block` only carries the human-readable reason — comments are the durable annotation channel. Reviewer either approves and runs `hermes kanban unblock \u003Cid>` (which re-spawns you with the comment thread for any follow-ups) or asks for changes via another comment.\n\n```python\nimport json\n\nkanban_comment(\n    body=\"review-required handoff:\\n\" + json.dumps({\n        \"changed_files\": [\"rate_limiter.py\", \"tests\u002Ftest_rate_limiter.py\"],\n        \"tests_run\": 14,\n        \"tests_passed\": 14,\n        \"diff_path\": \"\u002Fpath\u002Fto\u002Fworktree\",  # or PR url if pushed\n        \"decisions\": [\"user_id primary, IP fallback for unauthenticated requests\"],\n    }, indent=2),\n)\nkanban_block(\n    reason=\"review-required: rate limiter shipped, 14\u002F14 tests pass — needs eyes on the user_id\u002FIP fallback choice before merging\",\n)\n```\n\nUse `kanban_complete` only when the task is genuinely terminal — e.g. a one-line typo fix, a docs change with no functional consequences, or a research task where the artifact IS the writeup itself.\n\n**Research task:**\n```python\nkanban_complete(\n    summary=\"3 competing libraries reviewed; vLLM wins on throughput, SGLang on latency, Tensorrt-LLM on memory efficiency\",\n    metadata={\n        \"sources_read\": 12,\n        \"recommendation\": \"vLLM\",\n        \"benchmarks\": {\"vllm\": 1.0, \"sglang\": 0.87, \"trtllm\": 0.72},\n    },\n)\n```\n\n**Review task:**\n```python\nkanban_complete(\n    summary=\"reviewed PR #123; 2 blocking issues found (SQL injection in \u002Fsearch, missing CSRF on \u002Fsettings)\",\n    metadata={\n        \"pr_number\": 123,\n        \"findings\": [\n            {\"severity\": \"critical\", \"file\": \"api\u002Fsearch.py\", \"line\": 42, \"issue\": \"raw SQL concat\"},\n            {\"severity\": \"high\", \"file\": \"api\u002Fsettings.py\", \"issue\": \"missing CSRF middleware\"},\n        ],\n        \"approved\": False,\n    },\n)\n```\n\nShape `metadata` so downstream parsers (reviewers, aggregators, schedulers) can use it without re-reading your prose.\n\n## Shipping deliverables (`artifacts=[...]`)\n\nIf your task produced files a human actually wants — a chart, a PDF, a spreadsheet, a generated image, an archive — pass their **absolute paths** to `kanban_complete(artifacts=[...])`. The gateway notifier uploads each one as a native attachment to whoever subscribed to the task, so the deliverable lands in their chat alongside the completion message instead of being a path they have to go fetch.\n\n```python\nkanban_complete(\n    summary=\"Q3 revenue analysis: 14% QoQ growth, EMEA the laggard. Chart + full PDF attached.\",\n    artifacts=[\"\u002Ftmp\u002Fq3-revenue.png\", \"\u002Ftmp\u002Fq3-report.pdf\"],\n    metadata={\"rows_analyzed\": 48000, \"growth_qoq\": 0.14},\n)\n```\n\nImages and video embed inline; PDFs, docx, csv\u002Fxlsx\u002Fjson\u002Fyaml, pptx, zip\u002Ftar\u002Fgz, audio, and html upload as files. Rules:\n\n- **Absolute paths only**, and the file must still exist when you complete — don't point at a scratch file you already deleted.\n- **Only real deliverables.** Skip intermediate logs, scratch files, and inputs the human already has.\n- `artifacts` is the **top-level** parameter the notifier reads. Do not bury deliverable paths in `metadata` (e.g. `metadata.codex_lane.artifacts`) and expect them to upload — the notifier only scans the top-level `artifacts` list, with a best-effort fallback over your `summary`\u002F`result` text. Metadata paths are for downstream-worker bookkeeping, not delivery.\n- A bare string is auto-promoted to a one-element list, and it merges with any pre-existing `metadata.artifacts` without dupes.\n\nSame primitive works outside kanban: any agent surface delivers a file just by writing its absolute path into the response, and Slack\u002FDiscord\u002FTelegram\u002Fetc. upload it natively — the `artifacts` param is the structured kanban entry point.\n\n## Claiming cards you actually created\n\nIf your run produced new kanban tasks (via `kanban_create`), pass the ids in `created_cards` on `kanban_complete`. The kernel verifies each id exists and was created by your profile; any phantom id blocks the completion with an error listing what went wrong, and the rejected attempt is permanently recorded on the task's event log. **Only list ids you captured from a successful `kanban_create` return value — never invent ids from prose, never paste ids from earlier runs, never claim cards another worker created.**\n\n```python\n# GOOD — capture return values, then claim them.\nc1 = kanban_create(title=\"remediate SQL injection\", assignee=\"security-worker\")\nc2 = kanban_create(title=\"fix CSRF middleware\", assignee=\"web-worker\")\n\nkanban_complete(\n    summary=\"Review done; spawned remediations for both findings.\",\n    metadata={\"pr_number\": 123, \"approved\": False},\n    created_cards=[c1[\"task_id\"], c2[\"task_id\"]],\n)\n```\n\n```python\n# BAD — claiming ids you don't have captured return values for.\nkanban_complete(\n    summary=\"Created remediation cards t_a1b2c3d4, t_deadbeef\",  # hallucinated\n    created_cards=[\"t_a1b2c3d4\", \"t_deadbeef\"],                   # → gate rejects\n)\n```\n\nIf a `kanban_create` call fails (exception, tool_error), the card was NOT created — do not include a phantom id for it. Retry the create, or omit the id and mention the failure in your summary. The prose-scan pass also catches `t_\u003Chex>` references in your free-form summary that don't resolve; these don't block the completion but show up as advisory warnings on the task in the dashboard.\n\n## Block reasons that get answered fast\n\nBad: `\"stuck\"` — the human has no context.\n\nGood: one sentence naming the specific decision you need. Leave longer context as a comment instead.\n\n```python\nkanban_comment(\n    task_id=os.environ[\"HERMES_KANBAN_TASK\"],\n    body=\"Full context: I have user IPs from Cloudflare headers but some users are behind NATs with thousands of peers. Keying on IP alone causes false positives.\",\n)\nkanban_block(reason=\"Rate limit key choice: IP (simple, NAT-unsafe) or user_id (requires auth, skips anonymous endpoints)?\")\n```\n\nThe block message is what appears in the dashboard \u002F gateway notifier. The comment is the deeper context a human reads when they open the task.\n\n## Heartbeats worth sending\n\nGood heartbeats name progress: `\"epoch 12\u002F50, loss 0.31\"`, `\"scanned 1.2M\u002F2.4M rows\"`, `\"uploaded 47\u002F120 videos\"`.\n\nBad heartbeats: `\"still working\"`, empty notes, sub-second intervals. Every few minutes max; skip entirely for tasks under ~2 minutes.\n\n## Retry scenarios\n\nIf you open the task and `kanban_show` returns `runs: [...]` with one or more closed runs, you're a retry. The prior runs' `outcome` \u002F `summary` \u002F `error` tell you what didn't work. Don't repeat that path. Typical retry diagnostics:\n\n- `outcome: \"timed_out\"` — the previous attempt hit `max_runtime_seconds`. You may need to chunk the work or shorten it.\n- `outcome: \"crashed\"` — OOM or segfault. Reduce memory footprint.\n- `outcome: \"spawn_failed\"` + `error: \"...\"` — usually a profile config issue (missing credential, bad PATH). Ask the human via `kanban_block` instead of retrying blindly.\n- `outcome: \"reclaimed\"` + `summary: \"task archived...\"` — operator archived the task out from under the previous run; you probably shouldn't be running at all, check status carefully.\n- `outcome: \"blocked\"` — a previous attempt blocked; the unblock comment should be in the thread by now.\n\n## Notification routing\n\nYou can configure the gateway to receive cross-profile Kanban task notifications by adding `notification_sources` to `~\u002F.hermes\u002Fconfig.yaml`.\n- `notification_sources: ['*']` accepts subscriptions from all profiles.\n- `notification_sources: ['default', 'zilor-ppt']` or `\"default,zilor-ppt\"` restricts subscriptions to specified profiles.\n- Omitting the key keeps the default behavior (profile isolation).\n\n## Do NOT\n\n- Call `delegate_task` as a substitute for `kanban_create`. `delegate_task` is for short reasoning subtasks inside YOUR run; `kanban_create` is for cross-agent handoffs that outlive one API loop.\n- Call `clarify` to ask the human a question. You are running headless — there is no live user to answer. The call will time out (default ~120s) and the task will sit silently in `running` with no signal that it needs input. Use `kanban_comment` (context) + `kanban_block(reason=...)` (decision needed) instead — the task surfaces on the board as blocked, the operator sees it, unblocks with their answer in a comment, and you respawn with the thread.\n- Modify files outside `$HERMES_KANBAN_WORKSPACE` unless the task body says to.\n- Create follow-up tasks assigned to yourself — assign to the right specialist.\n- Complete a task you didn't actually finish. Block it instead.\n\n## Pitfalls\n\n**Task state can change between dispatch and your startup.** Between when the dispatcher claimed and when your process actually booted, the task may have been blocked, reassigned, or archived. Always `kanban_show` first. If it reports `blocked` or `archived`, stop — you shouldn't be running.\n\n**Workspace may have stale artifacts.** Especially `dir:` and `worktree` workspaces can have files from previous runs. Read the comment thread — it usually explains why you're running again and what state the workspace is in.\n\n**Don't rely on the CLI when the guidance is available.** The `kanban_*` tools work across all terminal backends (Docker, Modal, SSH). `hermes kanban \u003Cverb>` from your terminal tool will fail in containerized backends because the CLI isn't installed there. When in doubt, use the tool.\n\n## CLI fallback (for scripting)\n\nEvery tool has a CLI equivalent for human operators and scripts:\n- `kanban_show` ↔ `hermes kanban show \u003Cid> --json`\n- `kanban_complete` ↔ `hermes kanban complete \u003Cid> --summary \"...\" --metadata '{...}'`\n- `kanban_block` ↔ `hermes kanban block \u003Cid> \"reason\"`\n- `kanban_create` ↔ `hermes kanban create \"title\" --assignee \u003Cprofile> [--parent \u003Cid>]`\n- etc.\n\nUse the tools from inside an agent; the CLI exists for the human at the terminal.\n",{"name":5,"version":24,"metadata":25,"platforms":35,"description":7,"environments":39},"2.0.0",{"hermes":26},{"tags":27,"related_skills":33},[28,29,30,31,32],"kanban","multi-agent","collaboration","workflow","pitfalls",[34],"kanban-orchestrator",[36,37,38],"linux","macos","windows",[28],"main","2e6aa8d15ab0a366c90be54f61bf9c6e97015e83","skills\u002Fdevops\u002Fkanban-worker",1,"https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet","steadfaste.com","https:\u002F\u002Fgithub.com\u002Flukemcqueen","AI Architect | Building Hermes Cortex: governed multi-agent AI for autonomous software engineering | Enterprise Tech Consultant","2026-11-14 22:33:34",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add lukemcqueen\u002Fsteadfaste-fleet --skill kanban-worker",{"tool":55,"command":56},"bunx","bunx skills add lukemcqueen\u002Fsteadfaste-fleet --skill kanban-worker",{"tool":58,"command":59},"pnpm","pnpm dlx skills add lukemcqueen\u002Fsteadfaste-fleet --skill kanban-worker","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fkanban-worker\u002FSKILL.md",true,[],[64,72,79,86,93,100],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":71},"01M7DXY4G8NSVB59K8B6S2AQNP","macbook-linux-maintenance","Legacy MacBook Linux fixes: GPU wedge, reboot hang, thermal.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fmacbook-linux-maintenance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":71},"01M7DXXYJCXFJ3TGB84ZQ8KFE6","governance-regression-triage","Triage a host's governance issues: what changed.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fgovernance-regression-triage\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":71},"01M7DXXSAP1G8FDRJAMXQGBBMK","enforcement-immutability","Use when enforcement files lose their immutable flag.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fenforcement-immutability\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":71},"01M78SSDQVRYX64Y16X32TC0NS","steadfaste-fleet-repo-deploy","Use when committing to the steadfaste-fleet repo.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fsteadfaste-fleet-repo-deploy\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":71},"01M78SS928F3R2RJAYVW4E30CE","steadfaste-fleet-maintenance","Maintain an installed Steadfaste Fleet instance — update both the upstream Hermes Agent and the fleet repo layer, merge diverged histories, sync skills safely, and troubleshoot common issues. Covers the dual-update workflow (hermes update + fleet-update.sh), encrypted brain data backup, mycortex import, and recovery techniques.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fsteadfaste-fleet-maintenance\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":71},"01M78SP1CHW0T0BWE5ZT6JBPX8","fleet-preflight","DEPRECATED alias — merged into survey-before-action (2026-08-20). Load survey-before-action instead; its \"Repo-Specific Pre-Flight\" section covers git search, Hermes boundary, and deployment verification.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Ffleet-preflight\u002FSKILL.md",[],[]]