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 paultyng/skill-issue --skill review-performancegit clone --depth 1 https://github.com/paultyng/skill-issueWrote 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/paultyng/skill-issue/review-performance)<a href="https://agentmods.dev/skills/paultyng/skill-issue/review-performance"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/review-performance/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/paultyng/skill-issue/review-performance"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/review-performance.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 | $0.02010 |
| Opus 5.5 | $0.00030 | $0.00804 |
| Sonnet 5.5 | $0.00015 | $0.00402 |
| Haiku 4.5 | $0.00007 | $0.00201 |
Grade A, and why
review-performance scanned grade A with 1 finding 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Findings must cite probed evidence (`path:line`, grep output, command result), not pattern-matched suspicion. Per `~/.claude/rules/probe-not-assume.md`. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Review
Structured review of hot-path performance, allocation patterns, and benchmark coverage. Opt-in only — performance is rarely the bottleneck for new code, and a perf review on every PR is noise. Run when the user explicitly asks, or when a feature is performance-sensitive by nature (hot path, fanout, large-data).
Out of scope (defer to siblings):
- Concurrency safety (race, deadlock, leak) →
review-reliability - Cardinality / metric cost →
review-observability - Database query plans / index design →
review-database
review-performance looks at code-level allocation and CPU hotspots, benchmark sufficiency, and obvious algorithmic complexity issues.
Workflow
1. Scope and explore
- Confirm scope with the user: full codebase, specific packages/directories, changed files only (PR or branch diff), or a specific hot path.
- Resolve scope. Same conventions as siblings:
- Changed files (PR or branch):
git diff --name-only --diff-filter=d <base>...HEAD; filter to source files. - Explicit paths/packages: include all relevant source files.
- Full codebase: walk source files.
- Changed files (PR or branch):
- If invoked from review-all (only when the user opted in): receive
file_list,package_paths,has_changes,base_ref,REVIEW_DIR, andpr_url.
This skill is primarily Go-focused because the existing review-* corpus targets Go; it has cross-language sections in reference.md but the deepest checklist is for Go.
2. System overview
Produce a brief summary covering:
- Languages and runtimes in scope
- Identifiable hot paths (RPC handlers, queue consumers, batch jobs)
- Existing benchmark coverage (Go:
Benchmark*functions; presence oftesting.B) - Observed SLOs / latency targets if documented in
REVIEW.md,README.md, or runbooks
3. Launch investigation subagent
Launch a single investigation subagent (subagent_type="generalPurpose", model: sonnet per subagent-model-routing) with the system overview and in-scope file list.
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.
- 1mo ago First seen · 166 lines · 74 tokens per session scan A 7b9cc5bf79e3
review-performance is a skill published in the GitHub repository paultyng/skill-issue (8 stars, last pushed 4d ago), licensed MIT. It adds 74 tokens to every session and 2,010 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
megalinter-check
Collect MegaLinter lint errors for the current repository. Use when the user wants to know if the code passes linting, why the MegaLinter CI job fails, or before/after fixing lint errors. Two modes - watch a CI job (GitHub Actions, GitLab CI, Azure Pipelines, Bitbucket Pipelines) and parse its logs, or run MegaLinter…
megalinter-setup
Install or upgrade MegaLinter on a repository. Use when the user wants to add MegaLinter to a project, set up linting CI, update MegaLinter configuration or version, or says "install megalinter", "setup linting", "add code quality checks", "update megalinter skills". Always goes through npx mega-linter-runner…
chrome-devtools
Use Chrome DevTools MCP to control and inspect a live Chrome instance for network, console, performance, rendering, and Deep debugging. Pairs with playwright-cli (deterministic interaction/E2E) — complements, not duplicates.
gh-fix-ci
Diagnose failing GitHub Actions checks on a PR via gh, summarize the failure context, propose a plan, and only implement after explicit user approval. External CI providers (Buildkite, CircleCI, etc.) are reported by URL only.
playwright-cli
Drive a real browser from the terminal using the Playwright CLI (snapshot, click, fill, screenshots, traces). Use when the task is CLI-first browser automation (data extraction, UI debugging, form fills, multi-tab work). For Playwright test specs, use e2e-runner instead.