work

An automated worker loop for story-workflow projects, where a story is a tracked piece of development work. It claims ready stories, implements each in its own worktree—a separate working copy—and sends them through verification gates.

In plain words
What is it for?
Completing all stories, an epic, or selected story IDs; implementing each story separately; and continuing through verification until the goal is met or available limits are reached.
Why use it?
It coordinates repeated implementation and review work without manually managing claims, locks, or board updates. The workflow also limits workers to the commands and files intended for board changes.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/shousper/claude-kit/work
Any agent
npx skills add shousper/claude-kit --skill work
Clone the repo
git clone --depth 1 https://github.com/shousper/claude-kit

Made for: Claude Code, Codex.

Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,223 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 69a338802a20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 1 executable file (plan.workflow.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/stories/skills/work/SKILL.md · 170 lines

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

  1. 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.
  2. 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.
  3. 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.

Read the full file on GitHub · 170 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 170 lines · 146 tokens per session scan A 69a338802a20

Subscribe to this mod's changes

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.

Related

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…

kirodotdev/KiroCrew · 137 tokens

agile-product-owner

../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

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.

agentscope-ai/AgentTeams · 56 tokens

dot-ai-prd-create

Create documentation-first PRDs that guide development through user-facing content.

vfarcic/dot-ai · 18 tokens

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…

NVIDIA/elements · 115 tokens

bmad-check-implementation-readiness

Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".

delorenj/mcp-server-trello · 32 tokens