Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/shousper/claude-kit/worknpx skills add shousper/claude-kit --skill workgit clone --depth 1 https://github.com/shousper/claude-kitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00146 | $0.03223 |
| Opus 5 | $0.00073 | $0.01612 |
| Sonnet 5 | $0.00029 | $0.00645 |
| Haiku 4.5 | $0.00015 | $0.00322 |
Grade A, and why
work scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Worker
You are one worker in a possibly-parallel pool. The story CLI arbitrates everything shared — claims, locks, gates, integration. Your job is judgment and implementation.
Core principle: the loop is encoded — CLI + Stop hook drive continuation. You execute one story per iteration well; you never improvise orchestration.
HARD GATE: the CLI is the only writer
Never Edit/Write files under the configured storiesDir (default stories/), .claude/story-loop.*.local.md, .claude/story-state.local.json, .claude/story-learnings.local.md, or .claude/story-evidence/. Every board mutation is a story command. A PreToolUse hook denies direct writes — treat a denial as a redirect and run the CLI command it names. Do not route around it with Bash (sed -i, echo >>, heredocs): unlocked writes corrupt the board for every parallel worker.
Starting a run
- Parse the goal scope from the ask: whole board ("complete all stories"), an epic (
epic:st-9c01), an explicit list of ids, or a single story. - Multi-story goal →
story loop start --goal "<scope>". The CLI binds the loop to YOUR session (via CLAUDE_SESSION_ID) — only this session receives its re-prompts, and other sessions' loops never address you. The Stop hook now re-prompts you with the next story after each iteration — never "keep going" on your own initiative, and never touch the loop state files. - Single-story ask → skip the loop; run one iteration of the procedure below.
Iteration procedure
One story per iteration, in this order:
1. Pick
story ready --json. Feedback items rank first — take the top entry. Empty set → summarize why via story board (everything done, blocked, or in-review) and end your turn; the loop tick decides whether the goal is met.
2. Claim
story claim <id> — verifies readiness under lock, writes your lease, creates .worktrees/st-<id> on branch story/st-<id>. Lost the race (claim error) → re-run story ready and take the next. Never work on a story you have not claimed.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 170 lines · 146 tokens per session scan A 69a338802a20
work is a skill published in the GitHub repository shousper/claude-kit (4 stars, last pushed 6d ago), licensed MIT. It adds 146 tokens to every session and 3,223 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
teamharness-task-delegation
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
dot-ai-prd-create
Create documentation-first PRDs that guide development through user-facing content.
agent-upkeep
Perform one small, scoped maintenance improvement to the Elements monorepo and open a single reviewable pull request. Use this skill for scheduled or unattended upkeep runs that improve unit test coverage for one file, fix one behavioral bug in one module, or move one off ESLint rule toward enforcement to reduce…
bmad-check-implementation-readiness
Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".