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.
git clone --depth 1 https://github.com/ncoevoet/claude-review-allWrote 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/agents/ncoevoet/claude-review-all/07-performance)<a href="https://agentmods.dev/agents/ncoevoet/claude-review-all/07-performance"><img src="https://agentmods.dev/badge/agents/ncoevoet/claude-review-all/07-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/agents/ncoevoet/claude-review-all/07-performance"><img src="https://agentmods.dev/badge/agents/ncoevoet/claude-review-all/07-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 | $0.00037 | $0.00869 |
| Opus 5 | $0.00018 | $0.00434 |
| Sonnet 5 | $0.00007 | $0.00174 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
performance 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 7: Performance
Analyze changed code for performance regressions and resource leaks.
Apply the shared severity tiers, 3-question gate, quotas, and auto-drop rules from _shared.md.
Inputs you receive: full diff, changed file list, Project Profile, CLAUDE.md rules, Phase 1 gate results.
Algorithmic & I/O
- N+1 patterns: loop over collection issuing query/fetch per item — flag with concrete fix (batch / join /
Promise.all) - Big-O regressions: nested loops over same large collection that could be a hash join;
.includes()inside loop on large list (use a Set) - Repeated work: same expensive call inside loop or render that should be hoisted/memoized
- Sync I/O on hot path: blocking file/network calls in request handlers, render functions, or signal effects
- Blocking call while holding a lock: remote/IO/
sleepinside asynchronized/Lockblock serializes every caller behind one round-trip → contention, thread starvation. Hoist the call out of the critical section (cache or pre-fetch the value). - Exception as control flow in a hot loop: throwing+catching (e.g.
NoSuchMethodException, parse failures) on each iteration as normal flow → repeated stack-fill/allocation cost. Use a non-throwing check, or cache hits and misses.
Framework-specific (auto-detect from Project Profile)
Angular / signals
- Computed/effect reading signals it doesn't depend on (overzealous re-execution)
- Functions called from templates without
@letor memoization (re-runs every CD cycle) - Subscriptions without
takeUntilDestroyed/asyncpipe /DestroyRef(memory leak) Object.keys/array.filterinline in templates instead ofcomputed()- Missing
trackByon@forloops over large lists ChangeDetectionStrategy.Defaultreintroduced where parent usesOnPush
React
- Missing
useMemo/useCallbackfor non-primitive props passed to memoized children - New object/array literals in deps arrays
- Effects without cleanup that subscribe / set timers
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.
- 5d ago Changed · +1 lines f4156395eda1
- 9d ago First seen · 67 lines · 37 tokens per session scan A 1a327e4e471f
performance is an agent published in the GitHub repository ncoevoet/claude-review-all (25 stars, last pushed 7d ago), licensed MIT. It adds 37 tokens to every session and 869 once invoked, about $0.0002 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 agents, from other repositories
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
legal-reviewer
Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
accounting-reviewer
Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
tax-reviewer
Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
voice-ai-reviewer
Voice-AI / telephony pre-implementation reviewer. Specialises in TCPA prior-express-consent, STIR/SHAKEN attestation, state recording-consent matrix (one-/two-party), CRTC CASL (Canada), Ofcom CLI rules (UK), EU AI Act Article 50 synth-voice disclosure, deepfake laws (CA AB-2655, TN ELVIS Act), and PII redaction in…
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…