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/iampawan/manifest/canarygit clone --depth 1 https://github.com/iampawan/ManifestWrote 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/iampawan/manifest/canary)<a href="https://agentmods.dev/commands/iampawan/manifest/canary"><img src="https://agentmods.dev/badge/commands/iampawan/manifest/canary.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 5.1 | $0.00051 | $0.00508 |
| Opus 5 | $0.00026 | $0.00254 |
| Sonnet 5 | $0.00010 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
canary 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 5d 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
/canary
The face of the canary "orchestrator." For a feature currently rolling out, it shows the current stage, how long it has baked, the latest health verdict, and the next recommended step — which a human then performs by flipping the flag.
Usage
/canary SC-005
What it shows
- Current stage —
currentRolloutPercentand how long it's been at that stage vs the stage'sholdHoursbake time. - Health — the latest
rollback-guardverdict (proceed / hold / recommend-rollback) and the breached/warning signals, if any. - Next step — from the
rolloutPlan(contract frontmatter, elserepos.ymlconventions.rolloutPlan):- healthy + baked → "advance flag
<name>10% → 50%" - healthy, not baked → "hold at 10% — N more hours before advancing"
- warning → "hold and investigate
<signal>" - breach → "flip flag OFF / redeploy
<previous tag>" - final stage → "ramp complete — launch-monitor takes over"
- healthy + baked → "advance flag
Important
This is a recommend-and-approve loop. Manifest never advances or
pauses the flag for you — advancing a rollout is a production change you
own. /canary (and the rollback-guard.yml cron behind it) give you
the call and the exact action; you flip the flag in your flag system,
and the guard records the new currentRolloutPercent.
If your project has no feature-flag system, there's no staged ramp —
verify-deploy's "ready" verdict means "ready to deploy," and rollback
is a manual revert.
See also
/rollback-check <ID>— run a fresh health check now/verify-deploy <ID>— the pre-rollout readiness verdictreference/CONTRACT-FORMAT.md—rolloutPlan,currentRolloutPercent
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.
- 5d ago First seen · 50 lines · 51 tokens per session scan A b8b5bb6fe631
canary is a command published in the GitHub repository iampawan/Manifest (5 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 508 once invoked, about $0.0003 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 commands, from other repositories
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.