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 shennawardana23/skillme --skill code-reviewgit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/code-review)<a href="https://agentmods.dev/skills/shennawardana23/skillme/code-review"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/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/shennawardana23/skillme/code-review"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/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 | $0.00074 | $0.00852 |
| Opus 5 | $0.00037 | $0.00426 |
| Sonnet 5 | $0.00015 | $0.00170 |
| Haiku 4.5 | $0.00007 | $0.00085 |
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 8d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Review changes in a fixed order — security first, since a maintainability issue costs refactor time but a missed injection or auth gap costs a breach. Work through every category even for a small diff; skipping categories on "obviously small" changes is how small changes ship real bugs.
Phase 1 — context
Before judging anything, establish: what language/framework conventions apply, what problem the change solves, and its scope (feature, fix, refactor, security, performance).
Phase 2 — review order
- Security — input validation, authN/authZ on every new endpoint or operation, injection risk (SQL, command, template), secrets in code or logs, path traversal in file operations.
- Correctness — business logic matches the stated intent, boundary conditions (empty input, max values, concurrent access), error paths are handled and tested, no silent failures.
- Performance — no new unbounded loops over unbounded data, no leaked resources (unclosed files/connections, growing slices/maps held forever), caching invalidation is correct if caching was touched.
- Maintainability — functions stay focused, names carry intent without needing an explanatory comment, no duplicated logic, public APIs are documented.
- Tests — new behavior is tested, error paths are tested, table-driven (Go) or parameterized (JS/TS/PHP) tests used for input variations.
Gotchas
- For PostgreSQL tables partitioned by
hotel_idin this organization's schemas, a missinghotel_idfilter is a correctness AND a performance defect simultaneously — the query engine scans every partition instead of pruning to one. Flag this even if the query "looks" correct. See thepostgres-hotel-partitioningskill for the specific patterns to check. - A change that only touches test files or comments still needs the Security pass if it changes what a test asserts — a weakened assertion ("skip this check in CI") is a security regression disguised as test maintenance.
- Identical-looking conditional branches are the highest-value thing to
read character-by-character, not skim: Apple's 2014 "goto fail" SSL bug
was a single duplicated
goto fail;line that caused certificate validation to always succeed, silently, for over a year — the kind of defect that is invisible on a fast skim and only surfaces on a careful line-by-line read of a short, unremarkable-looking function.
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.
- 8d ago First seen · 85 lines · 74 tokens per session scan A 7fe45e2fda27
code-review is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 74 tokens to every session and 852 once invoked, about $0.0004 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
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
review-loop
Bounded review-apply-resolve convergence loop for a GitHub PR (draft PRs are fine). Runs up to N=5 iterations of pr-reviewer → implement-suggestion (--resolve-all) → polish simplify, converging until every review thread is resolved — through a fix OR a reply (answered question, recorded rationale) — so the PR is left…
implement-suggestion
Implements review-comment suggestions across one or more PRs. Multi-PR mode (default when $ARGUMENTS contains PR URLs; empty $ARGUMENTS auto-detects the active PR) per PR: resolves a worktree, fetches every actionable comment from both human teammates AND AI code-review bots (claude[bot], coderabbitai[bot], …)…
create-pr
Generates a short, narrative GitHub pull request description (≤ 25 lines, hard ceiling 40), pushes the branch, opens the PR as a draft, then runs review-loop (pr-reviewer → implement-suggestion → polish simplify, up to 5 iterations) until every review thread is resolved via fix or reply. Scale down with --no-review…
confidence
Rates confidence that the current work fully solves the stated requirement. Supports plan validation, code review, and analysis (root-cause, refactor, diagnose) modes. Plan mode combines LLM judgment with deterministic rule checks (multi-signal gate); a failed rule caps the gate at 89% regardless of LLM score. Use…