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/code-reviewgit clone --depth 1 https://github.com/iampawan/ManifestWhat 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 | $0.00041 | $0.00407 |
| Opus 5 | $0.00020 | $0.00204 |
| Sonnet 5 | $0.00008 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
code-review 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 2d 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
/code-review
Runs the code-review skill against a PR diff. This is the
code-quality half of PR verification — it asks "is the code sound?"
where /verify-pr asks "does it satisfy the contract?" Both run on
the same PR; neither replaces the other.
Usage
/code-review 123
/code-review https://github.com/<org>/<repo>/pull/123
What it does
- Fetches the PR diff via GitHub MCP and resolves the repo's stack
from
repos.yml(review is stack-appropriate). - Loads the contract revision so the diff is reviewed against intent.
- Walks the diff for security, correctness, performance, and maintainability defects.
- Emits
CR-findings (closed severity enum: blocker/warning/info), validated byscripts/validate.mjs --check-review— out-of-schema output is rejected, open blockers gate the merge. - Writes
.manifest/contracts/<ID>.pr-review.mdand posts a PR review comment with the findings table.
When to use
- After the Implementer opens the PR, alongside
/verify-pr. - Runs automatically on every push via
pr-verify.yml. - Open blockers feed the review→fix loop: the Implementer addresses
them automatically and re-pushes (see
/implementand GUIDE.md).
See also
/verify-pr— AC/contract conformance on the same PR/implement— the Implementer, including review→fix modereference/CRITIC-PROTOCOL.md— the shared severity enum
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.
- 2d ago First seen · 45 lines · 41 tokens per session scan A 45bc768c421a
code-review is a command published in the GitHub repository iampawan/Manifest (5 stars, last pushed 20d ago), licensed MIT. It adds 41 tokens to every session and 407 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 2026-08-31.
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.