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/flz/iaqualink-py/reviewgit clone --depth 1 https://github.com/flz/iaqualink-pyWrote 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/flz/iaqualink-py/review)<a href="https://agentmods.dev/commands/flz/iaqualink-py/review"><img src="https://agentmods.dev/badge/commands/flz/iaqualink-py/review.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 | $0.00025 | $0.00543 |
| Opus 5 | $0.00013 | $0.00271 |
| Sonnet 5 | $0.00005 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/review
Run the review rubric against the current branch.
Steps
1. Get the diff
git fetch origin master 2>/dev/null || true
BASE=$(git merge-base HEAD origin/master 2>/dev/null \
|| git rev-list --max-parents=0 HEAD)
git diff "$BASE"...HEAD
If the diff is empty, report "No changes vs master" and stop.
2. §0 — Confidentiality (hard blocker — check first)
Grep the diff for the patterns listed in .claude/review-criteria.md §0:
git diff "$BASE"...HEAD | grep -nP \
'\.java\b|com\.zodiac\.|com\.amazonaws\.|networkmodule/|iaqualinkandroid/|RetrofitClient\b|NetworkClient\b|SecurityUtils\b|ApiHelper\b|UserAuthenticationManager\b'
Any hit is a hard blocker. Report each match as §0 <file>:<line> — <match>. Do not proceed with the rest of the review if §0 fails.
3. §1 — Protocol Correctness
Invoke the architecture-auditor subagent with the diff. Pass the full diff text as context. Report its output verbatim under §1.
4. §2–§10 — Remaining rubric sections
Work through each remaining section of .claude/review-criteria.md in order (§2 Async Correctness through §10 Spec Validation). For each section:
- Read the diff against the criteria.
- Report issues as:
§<N> <file>:<line> — <one-line description> - If the section is clean:
§<N> LGTM
5. Summary
After all sections: print a one-line summary.
- If any blocker:
BLOCKED — fix §<N> before opening PR - If issues but no blockers:
ISSUES — address before merging - If all clean:
LGTM — ready for PR
Notes
- This command mirrors what the GitHub
claude-code-review.ymlbot runs on every PR. Running it locally closes the feedback loop before push. - Use
git push --no-verifyto skip the automated pre-push hook if you need to push work-in-progress. - To review a specific commit range: run
/reviewthen manually adjust theBASEref if needed.
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 · 57 lines · 25 tokens per session scan A 4d01071cf50a
review is a command published in the GitHub repository flz/iaqualink-py (45 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 25 tokens to every session and 543 once invoked, about $0.0001 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.