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/xiaolai/cc-suite/cancelgit clone --depth 1 https://github.com/xiaolai/cc-suiteWrote 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/commands/xiaolai/cc-suite/cancel)<a href="https://agentmods.dev/commands/xiaolai/cc-suite/cancel"><img src="https://agentmods.dev/badge/commands/xiaolai/cc-suite/cancel.svg" alt="Measured on agentmods" 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 | $0.00007 | $0.00714 |
| Opus 5 | $0.00003 | $0.00357 |
| Sonnet 5 | $0.00001 | $0.00143 |
| Haiku 4.5 | $0.00001 | $0.00071 |
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 4d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Workflow
Step 1: Resolve, terminate, and persist
One call resolves the reference (empty → the only active job; otherwise exact or prefix match among active jobs), terminates the job's process tree, confirms the exit, and records the cancellation:
node -e "
const { cancelJob } = await import('${CLAUDE_PLUGIN_ROOT}/scripts/lib/job-control.mjs');
try {
const reference = process.argv[1] || undefined;
const result = cancelJob(process.cwd(), reference);
console.log(JSON.stringify(result, null, 2));
} catch (error) {
console.error(error.message);
process.exitCode = 1;
}
" -- "$ARGUMENTS"
Do not shell out to kill directly. cancelJob verifies that the recorded PID still belongs to this job (via its recorded process start time) before signalling — a bare kill -- -{pid} on a recycled PID would terminate an unrelated process. It also escalates SIGTERM → SIGKILL and only reports success once the process is confirmed gone.
If the command errors:
"No active Codex jobs to cancel."→ relay it and STOP."Multiple jobs are active..."→ list the active jobs (viabuildStatusSnapshotas in/cc-suite:status) and STOP:Multiple jobs are active. Specify which one to cancel: | Job | Kind | Status | Elapsed | Summary | | --- | --- | --- | --- | --- | | {job-id} | {kind} | running | {elapsed} | {summary} | Usage: /cc-suite:cancel <job-id>"No job found for ..."/"...is ambiguous..."→ relay it and STOP.
Step 2: Report the actual outcome
The result carries outcome, terminated, and detail. Report what really happened rather than assuming the kill worked:
outcome |
Meaning | Report |
|---|---|---|
terminated |
Signalled and confirmed exited | Cancelled {job-id}. |
already-exited |
Process was already gone (or its PID had been recycled) | Cancelled {job-id} — it had already finished. |
not-confirmed |
SIGTERM and SIGKILL sent, process still alive | Cancelled {job-id} in the job list, but the process has not exited yet — {detail}. |
unverifiable |
Job predates process-identity tracking; not signalled | Marked {job-id} cancelled, but it was not signalled — {detail}. |
no-pid |
No PID recorded (queued, worker never started) | Marked {job-id} cancelled — {detail}. |
signal-failed |
Signalling raised an error | Marked {job-id} cancelled, but termination failed — {detail}. |
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.
- 4d ago First seen · 73 lines · 7 tokens per session scan A 332ed99482cd
cancel is a command published in the GitHub repository xiaolai/cc-suite (45 stars, last pushed yesterday), licensed ISC. It adds 7 tokens to every session and 714 once invoked, about $0.0000 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.