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 skills add wazimmerman/zimster --skill receiving-code-reviewgit clone --depth 1 https://github.com/wazimmerman/zimsterWrote 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/skills/wazimmerman/zimster/receiving-code-review)<a href="https://agentmods.dev/skills/wazimmerman/zimster/receiving-code-review"><img src="https://agentmods.dev/badge/skills/wazimmerman/zimster/receiving-code-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 | $0.00024 | $0.00456 |
| Opus 5 | $0.00012 | $0.00228 |
| Sonnet 5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
receiving-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 7d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Receiving Code Review
Review is independent evidence, not an authority ritual. Neither accept nor reject a finding based on tone, model identity, or inconvenience.
Process each finding
- Restate the technical claim.
- Locate the cited code and requirement.
- Reproduce or reason through the consequence.
- Classify it as valid, invalid, ambiguous, plan-conflicting, or missing evidence.
- Record the decision and proof.
Ask for clarification only when the finding cannot be made testable from its current wording.
Valid findings
Combine related Critical and Important findings into one correction wave. Ordinary accepted findings do not require separate user authorization for each deterministic local correction; use the configured correction-commit budget. Write or strengthen a failing proof where behavior is defective, then fix the underlying invariant. Run focused covering tests and affected integration checks.
A correction invalidates every affected evidence receipt and the prior exact-head semantic approval. Update the requirement-to-evidence matrix and review package for the corrected head before requesting the bounded recheck.
Do not make one agent or commit per finding when one owner understands the shared cause. Rejecting delegated implementation returns the correction to that owner; it does not automatically dispatch another implementer or alter routing policy.
Pushback
Push back when evidence shows the reviewer is wrong or the proposed fix would violate the mission. Cite:
- exact requirement or interface;
- code location;
- focused test or experiment;
- alternative interpretation and consequence.
“It's intentional,” “the plan said so,” and “tests pass” are not sufficient by themselves.
Contradictions
A real conflict between the review and an approved requirement belongs to the mission owner. Present both texts and the technical consequence. Do not quietly change product behavior to satisfy a generic rubric.
Recheck
Return the original finding batch and fix range to the same reviewer for one resumed recheck. If a load-bearing dispute remains, use the review circuit breaker rather than seeking fresh reviewers until one agrees.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 65 lines · 24 tokens per session scan A b47deb291856
receiving-code-review is a skill published in the GitHub repository wazimmerman/zimster (2 stars, last pushed 5d ago), licensed MIT. It adds 24 tokens to every session and 456 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 2026-08-31.
Other skills, from other repositories
security-audit
Security review and hardening workflow — root-cause analysis of vulnerabilities, authentication and authorization checks, least privilege, input handling, secret hygiene, and security regression tests. Use when reviewing code for security, fixing a vulnerability, hardening a feature, or handling auth, permissions…
safe-change
Trace, implement, test, and independently review one bounded software change. Use for ordinary feature, bug-fix, or refactor work after the repository is bootstrapped; do not use for broad repository cleanup, production operations, or undefined rewrites.
behavior-implement
Implement behavior through a red-green-refactor cycle when focused automated tests are proportionate. Use for product behavior changes and for engineering tooling and infrastructure only when native checks are insufficient and concrete complexity or failure risk warrants dedicated tests.
ai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode.
critique-theater
Five-role Design Jury review that streams scored rounds, persists a replayable transcript, and ships through the daemon's Critique Theater protocol.
nw-review
Dispatches an expert reviewer agent to critique workflow artifacts. Use when a roadmap, implementation, or step needs quality review before proceeding.