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 commands/theam/claude-dev-kit/work-storygit clone --depth 1 https://github.com/theam/claude-dev-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 | $0.00040 | $0.00571 |
| Opus 5 | $0.00020 | $0.00285 |
| Sonnet 5 | $0.00008 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
work-story 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 3d 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.
What it actually says
Work the user story given in the arguments: $ARGUMENTS
Delegate the workflow to the coding-agent subagent in two phases, passing the issue key and any extra instructions from the arguments.
Rules:
- If no issue reference is present in the arguments, ask for one — do not guess. Accept the reference shapes the configured tracker uses (e.g.
PROJ-1234for Jira,ENG-42for Linear,#123for GitHub Issues / Azure DevOps).
The story is worked in the current directory — no worktree is created here. To run several stories in parallel, use /launch-story first: it prepares a dedicated worktree and opens a new window, and this command runs inside it.
Phase 1 — context and plan. Instruct the coding-agent to fetch the ticket (and any linked designs), build its implementation plan, and RETURN the ticket summary and the full plan as its result — telling it explicitly NOT to ask for approval itself and NOT to write any code yet.
Plan-approval gate — two separate steps, in this exact order:
- FIRST, print the plan: write a normal assistant message to the conversation containing the ticket summary and the coding-agent's FULL plan, verbatim. This message is a hard requirement — a selection dialog is NOT a substitute for it, and putting the plan only inside a dialog's option text does not count: the user must be able to read the complete plan in the chat before any question appears.
- THEN, and only after that message is visible, ask the user to approve, adjust, or cancel (plain question or dialog — either is fine at this point).
Never collapse these two steps into one dialog. Only if the arguments contain --auto-approve (for automated/pipeline runs), skip the gate and proceed directly.
Phase 2 — execution. On approval (or auto-approve), continue the SAME coding-agent (resume it with the approval and any user adjustments) so it keeps its context, and let it run the remaining workflow: implement, verify gates, self-review, create the PR, and update the tracker ticket.
- Relay the coding-agent's final report to the user: PR URL, verification evidence (unit tests, coverage table, e2e results, lint, security pass), tracker transition applied, and follow-up risks.
- If the current directory is a
/launch-storyworktree, remind the user to remove it (git worktree remove <path>) once the PR merges.
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.
- 3d ago First seen · 28 lines · 40 tokens per session scan A ff340971d1de
work-story is a command published in the GitHub repository theam/claude-dev-kit (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 571 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
handoff
Hand off a bead to an AI agent for implementation.
skill-info
Get detailed information about a specific JIRA skill.
context-new
Create a new GitHub repository with AllBeads pre-configured.
onboard-repo
Interactive onboarding for a repository into AllBeads.
project-new
Plan a new project - create repo and beads, but don't code yet.
create
Create a bead in a specific context (cross-repo task handoff).