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-reviewergit 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-reviewer)<a href="https://agentmods.dev/skills/shennawardana23/skillme/code-reviewer"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/code-reviewer/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-reviewer"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/code-reviewer.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 | $0.00091 | $0.01615 |
| Opus 5 | $0.00046 | $0.00807 |
| Sonnet 5 | $0.00018 | $0.00323 |
| Haiku 4.5 | $0.00009 | $0.00161 |
Grade A, and why
code-reviewer 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 9d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
A mechanical, checklist-driven scan: walk every category below in order, record every match with a severity, then emit the report. This is a scanner, not a workflow — it does not cover change sizing, review etiquette, or process (see code-review-and-quality for that). It does not walk a security-priority checklist end to end (see security-review for that). Its distinguishing category is concurrency, which the other review skills in this catalog do not cover.
Category checklist
Work through every category for every changed file. Don't stop at the first finding — a diff with one CRITICAL often has MEDIUM issues too.
Correctness
- Logic bugs, off-by-one errors, wrong boundary conditions
- Missing nil/zero-value checks and unhandled edge cases
- Incorrect assumptions about a library's behavior — check the actual doc/signature, not intuition (e.g., does
strings.TrimSuffixno-op silently if the suffix doesn't match? yes — a common mis-assumption)
Security
- SQL/command/template injection via unsanitized input
- Hardcoded secrets, credentials, or API keys
- Insecure cryptographic choices (MD5/SHA1 for anything security-sensitive, ECB mode,
math/randfor tokens) - Missing authentication or per-resource authorization on new endpoints
- Path traversal, open redirects, SSRF-shaped calls (server fetches a user-influenced URL)
Error handling
- Errors silently swallowed (
_ = err) or logged but not propagated - Missing cleanup on error paths —
defer f.Close()placed before the error check, not after - Panic recovery missing in goroutines (an unrecovered panic in a goroutine crashes the whole process, not just that goroutine)
- Errors wrapped with
%wlosing sentinel-comparability, or not wrapped at all, losing context
Concurrency (Go)
- Data races: map or slice read/write from multiple goroutines without a mutex or
sync.Map. Don't just read the code — rungo test -raceand check the diff's package is covered. - Goroutine leaks: a goroutine started with no way for it to ever return — no
context.Context, nodonechannel, no bound on the channel it's blocked sending to. - Deadlocks: locks acquired in inconsistent order across two code paths; a channel send/receive with no counterpart and no
selectwith actx.Done()case. mu.Lock()not immediately followed bydefer mu.Unlock()on the next line — anything between them is a window where an early return skips the unlock.- A
WaitGroup.Addcall issued inside the goroutine it's supposed to be counting, instead of beforego func(){...}()— a benign-looking reorder that reintroduces the racego vet'sloopclosure/-racewon't always catch on the first run.
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.
- 9d ago First seen · 109 lines · 91 tokens per session scan A 55f88ab7d352
code-reviewer is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,615 once invoked, about $0.0005 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…
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…
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], …)…
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…