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 chipfighter/coding-discipline --skill code-reviewgit clone --depth 1 https://github.com/chipfighter/coding-disciplineWrote 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/chipfighter/coding-discipline/code-review)<a href="https://agentmods.dev/skills/chipfighter/coding-discipline/code-review"><img src="https://agentmods.dev/badge/skills/chipfighter/coding-discipline/code-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chipfighter/coding-discipline/code-review"><img src="https://agentmods.dev/badge/skills/chipfighter/coding-discipline/code-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00104 | $0.00614 |
| Opus 5.5 | $0.00042 | $0.00246 |
| Sonnet 5.5 | $0.00021 | $0.00123 |
| Haiku 4.5 | $0.00010 | $0.00061 |
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 1mo 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performing a review (review it yourself; delegate when worthwhile and supported)
When an independent perspective is needed and the current client supports subagents, you may delegate a review. Give the reviewer carefully scoped context (what changed, which requirements it should meet, and the base..head diff range), not the entire session history. Review small changes yourself; do not add agent overhead for appearances.
Review in this priority order. Do not dwell on a lower priority while a higher one is unresolved:
- Correctness: is the logic sound; are edge cases, errors, or concurrency missing; can it crash?
- Requirements: check each requirement and design point. Does the change do what was requested, and is anything missing?
- Security: injection, unauthorized access, secret leakage, unvalidated input.
- Simplicity: overengineering, duplication, removable dead code, features that are not needed yet.
- Style: naming, consistency, readability—review these last, not first.
Use severity: fix blockers (crashes/security) immediately, fix important issues before proceeding, and note minor issues for later.
Receiving review feedback
- Verify before changing anything: does this feedback apply to this codebase? Could it break existing behavior? Is there a reason the code is written this way? If uncertain, say, "I cannot verify X. Should I investigate, ask, or leave it for now?"
- Do not comply blindly: if a suggestion is wrong, lacks context, asks for something not needed yet, or conflicts with an established architecture decision, push back with technical reasons rather than changing it because a reviewer said so. Stop and consult someone when the conflict concerns architecture.
- No performative agreement: do not say "You're right!", "Good suggestion!", or "Thanks for catching that!" If you make the change, state what changed and where. If your pushback was wrong, say only, "I checked and I was wrong because X; I changed it." Do not write a long apology.
- If anything is unclear, clarify every item before making changes. Do not act only on the items you understand; review items are often related, and partial understanding leads to wrong changes.
- Address one item at a time, test each change, and confirm that it introduced no regressions (see verify-before-done).
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.
- 1mo ago First seen · 25 lines · 104 tokens per session scan A d5c1131268cc
code-review is a skill published in the GitHub repository chipfighter/coding-discipline (25 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 614 once invoked, about $0.0004 per session on Opus 5.5. 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
ccc-makeover
Score project health with $ccc-xray, apply the top recommendations one at a time with your OK, and show a before/after report card. Use when the user asks for a health check, wants the top issues fixed automatically, asks for a project score or report card, or types $ccc-makeover.
ccc-code-review
Alias for $ccc-review: forwards a code, PR or diff review request with its arguments to the canonical review workflow. Use when the user types $ccc-code-review or asks to review code, a PR, a file or a diff by this name.
pr-review-expert
Tier: POWERFUL Category: Engineering Domain: Code Review / Quality Assurance.
tech-debt-tracker
Scan codebases for technical debt, score severity, track trends, and generate prioritized remediation plans. Use when users mention tech debt, code quality, refactoring priority, debt scoring, cleanup sprints, or code health assessment. Also use for legacy code modernization planning and maintenance cost estimation.
connect
Install the scoped Antigravity permission hook.
pr
Analyze changes, detect scope issues, and create a well-structured PR.