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 chrisallenlane/claude-swe-workflows --skill review-perfgit clone --depth 1 https://github.com/chrisallenlane/claude-swe-workflowsWrote 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/chrisallenlane/claude-swe-workflows/review-perf)<a href="https://agentmods.dev/skills/chrisallenlane/claude-swe-workflows/review-perf"><img src="https://agentmods.dev/badge/skills/chrisallenlane/claude-swe-workflows/review-perf/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/chrisallenlane/claude-swe-workflows/review-perf"><img src="https://agentmods.dev/badge/skills/chrisallenlane/claude-swe-workflows/review-perf.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 | $0.00028 | $0.01524 |
| Opus 5 | $0.00014 | $0.00762 |
| Sonnet 5 | $0.00006 | $0.00305 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
review-perf 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 11d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Review
Advisory-only performance review. Detects whether the project contains web content, non-web source code, or both, and dispatches the appropriate performance reviewer(s). No changes are made.
Philosophy
Measure, don't guess. Performance intuitions are unreliable. The reviewers identify structural issues and recommend what to measure, not just what to optimize.
Two domains, one workflow. Compute performance (algorithms, memory, CPU) and web performance (network latency, caching, asset delivery) are fundamentally different disciplines. This skill dispatches the right specialist(s) for the project rather than applying one lens to everything.
Diagnostic, not therapeutic. This skill identifies performance problems and recommends fixes. It does not implement them. Ask for changes directly after reviewing the findings, or use /implement with the review as context.
Workflow Overview
┌──────────────────────────────────────────────────────┐
│ PERFORMANCE REVIEW │
├──────────────────────────────────────────────────────┤
│ 1. Detect project type (web, non-web, or both) │
│ 2. Determine scope │
│ 3. Dispatch performance reviewer(s) │
│ 4. Present consolidated report │
└──────────────────────────────────────────────────────┘
Workflow Details
1. Detect Project Type
Scan the project for source files to determine what performance domains apply.
Web indicators (any of these → dispatch web reviewer):
| Indicator | Signal |
|---|---|
.html, .htm, .jsx, .tsx, .vue, .svelte |
Strong |
package.json with web framework (react, vue, next, nuxt, astro, etc.) |
Strong |
webpack.config.*, vite.config.*, next.config.* |
Strong |
.css, .scss, .less files (more than a few) |
Moderate |
_headers, _redirects, vercel.json, netlify.toml |
Moderate |
Service worker files (sw.js, service-worker.js) |
Strong |
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.
- 11d ago First seen · 191 lines · 28 tokens per session scan A 5f1233ecc1f0
review-perf is a skill published in the GitHub repository chrisallenlane/claude-swe-workflows (18 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 1,524 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 2026-08-30.
Other skills, from other repositories
afc:issue
Analyze GitHub issue — investigate bug reports, understand requirements, inspect issues.
afc:doctor
Diagnose afc plugin setup and health.
afc:debug
Bug diagnosis and fix — root-cause analysis for errors, crashes, broken behavior.
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
hive.error-recovery
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…