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/verify-deploygit 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/verify-deploy)<a href="https://agentmods.dev/commands/iampawan/manifest/verify-deploy"><img src="https://agentmods.dev/badge/commands/iampawan/manifest/verify-deploy.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 | $0.00063 | $0.00599 |
| Opus 5 | $0.00032 | $0.00300 |
| Sonnet 5 | $0.00013 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
verify-deploy 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/verify-deploy [--env qa|preprod|prod]
Invokes the verify-deployment skill in live-URL mode against the given contract and environment.
Usage
/verify-deploy AUTH-1234 https://qa.example.com
/verify-deploy AUTH-1234 https://preprod.example.com --env preprod
/verify-deploy AUTH-1234 https://www.example.com --env prod
When to use it manually
The verify-deployment skill normally fires automatically when the
verify-deploy.yml workflow detects a successful deploy. Run it
manually when:
- You deployed via a path that doesn't trigger the workflow
(e.g., direct push to a static host, manual
vercel deploy). - You want to re-verify after fixing something post-deploy without doing another full deploy.
- You're piloting Manifest before installing the CI workflows.
- A deploy succeeded but the verifier comment didn't show up and you want to manually re-run.
What it does (vs /verify-pr)
/verify-pr runs static verification against a PR diff — it checks
whether the code touches the things the contract says it should,
whether ACs have tests mapped, whether instrumentation is wired.
No live execution. Fast.
/verify-deploy runs against a deployed environment — it actually
hits the URL with Playwright tests, samples Sentry for errors in
the window, samples analytics for event firing. It tells you
whether the deploy actually works, not just whether the diff
looks right. Slower (1–5 min).
You typically run /verify-pr during code review and
/verify-deploy after deploy.
Output
.manifest/contracts/<ID>.deploy-<env>-<timestamp>.md with:
- Per-AC pass/fail
- Event firing summary (which events fired, at what rate)
- Error rate vs budget
- A verdict:
ready-for-canary | hold | rollback
Plus a comment posted on the contract's tracking issue and a Slack ping.
Anti-patterns
- Don't run this against prod before canary completes — you'll
measure a partial population. Wait until rollout is at 100% (or
use
--env prod-canaryif you've stamped the canary tag). - Don't run this immediately after deploy — wait at least 60s for the deploy to start receiving traffic so the telemetry sample is meaningful.
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 · 68 lines · 63 tokens per session scan A af0b95828614
verify-deploy is a command published in the GitHub repository iampawan/Manifest (5 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 599 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
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.