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 skills add shousper/claude-kit --skill cancelgit clone --depth 1 https://github.com/shousper/claude-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shousper/claude-kit/cancel)<a href="https://agentmods.dev/skills/shousper/claude-kit/cancel"><img src="https://agentmods.dev/badge/skills/shousper/claude-kit/cancel/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shousper/claude-kit/cancel"><img src="https://agentmods.dev/badge/skills/shousper/claude-kit/cancel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.00673 |
| Opus 5.5 | $0.00035 | $0.00269 |
| Sonnet 5.5 | $0.00017 | $0.00135 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
cancel 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 1mo 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cancel Story Run
The escape hatch. Stopping is cheap, safe, and never loses work — say so, then do it.
Process
1. Stop the loop
Loops are per-session — stopping one worker's loop needs its session id (or run this from that worker's own session, whose harness adapter supplies it as STORY_SESSION_ID); stopping every loop on the board needs --all.
story loop status --json # no session: lists every active loop on the board
story loop status --session <id> --json # one worker's loop — capture goal, iteration count, and stalls vs budget BEFORE stopping
story loop stop --session <id> # stop that one worker's loop — returns {stopped: true|false}
story loop stop --all # stop every loop on the board
Report the goal, iteration count, and stalls-vs-budget from the status output. If status reports no active loop ({active: false}), say so and continue to the report — the human still wants the picture.
2. Settle the in-flight story
If this session has a claimed in-progress story, ask your human partner which of:
- Finish it — one last pass through gates and
story done. - Park it —
story park <id> --question "Cancelled mid-work: <current state, what remains>". - Release it —
story update <id> --status todo(work stays on the story branch; the worktree remains for the next claimant).
Never decide silently, and never leave it dangling without asking — a dead lease is reclaimable, but the next worker wastes time re-discovering state.
3. Report the board
From story board (and story list --json where detail helps):
- Counts: done / in-progress / in-review / blocked / todo.
- Parked questions, verbatim, with story ids — these are the human's inbox.
- In-review stories awaiting human review or PR merge.
- Other sessions' active claims — do NOT touch them; their leases expire on their own.
What cancel is not
- Not rollback: completed stories stay done; merged code stays merged.
- Not teardown: worktrees, branches, config, and learnings remain — a future stories:work run resumes cleanly.
- Not cleanup of other workers: parallel sessions keep running; stopping them means cancelling in THEIR sessions.
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.
- 1mo ago Changed 8610c536b639
- 1mo ago First seen · 57 lines · 87 tokens per session scan A 68cd9a583ba7
cancel is a skill published in the GitHub repository shousper/claude-kit (4 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 673 once invoked, about $0.0003 per session on Opus 5.5. 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
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…