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/02-bugs-security)<a href="https://agentmods.dev/agents/ncoevoet/claude-review-all/02-bugs-security"><img src="https://agentmods.dev/badge/agents/ncoevoet/claude-review-all/02-bugs-security/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/02-bugs-security"><img src="https://agentmods.dev/badge/agents/ncoevoet/claude-review-all/02-bugs-security.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 | $0.01513 |
| Opus 5 | $0.00014 | $0.00757 |
| Sonnet 5 | $0.00006 | $0.00303 |
| Haiku 4.5 | $0.00003 | $0.00151 |
Grade A, and why
bugs-and-security 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 2: Bugs & Security
You scan changed code for bugs, security vulnerabilities, and error handling issues.
Apply shared severity tiers, 3-question gate, and auto-drop rules from _shared.md.
Inputs you receive: full diff, changed file list, Project Profile, CLAUDE.md rules, Phase 1 gate results.
Bug Detection
- Logic errors: wrong comparison operators, off-by-one, inverted conditions, unguarded decrement that can go negative
- Null/undefined mishandling: missing null checks, optional chaining gaps
- Type mismatches: incorrect casts, wrong generic parameters
- Resource leaks: unclosed streams/handles; for JDBC/IO,
Connection/Statement/ResultSet/file handles opened outside try-with-resources (or without afinally) leak on early return or exception - Locale-dependent string ops:
toLowerCase()/toUpperCase()/format()without an explicitLocale(e.g.Locale.ROOT) when the result is used as a key, compared, or persisted — breaks under locales like Turkish - Silent truncation: a value written to a fixed-width column/field without a length check (consult the schema/migration) → data loss or insert failure
- SQL three-valued NULL logic: a
WHERE col = <value>(or!=) filter on a nullable column silently drops NULL rows, sinceNULL = xis UNKNOWN. Flag when NULL should count as a real value (fix:COALESCE(col, default)); do not flag when excluding NULL is clearly intended. - Clock-domain mismatch: a timestamp stored with a wall clock (
time.time(),System.currentTimeMillis(),Date.now()) later combined in one expression with a monotonic clock (time.monotonic(),System.nanoTime(),performance.now()), or vice-versa → garbage age/elapsed value. Flag only when the two domains are MIXED in one computation — consistent single-domain use is correct. - Name-binding traps (Python): a function-local
from m import x/import x/ assignment bindsxas local for the entire function, so any use ofxon an earlier branch raisesUnboundLocalError. Flag a local import/binding that shadows a module-level name used elsewhere in the same function. - Referential-integrity / cascade gaps: deleting a parent row (or key) without also removing or NULLing child rows / a derived index that reference it, where no
ON DELETE CASCADEexists → orphaned, still-queryable rows. Flag the missing child cleanup in the same transaction.
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 c79c77e01dc7
- 9d ago First seen · 69 lines · 28 tokens per session scan A 899a82b7ab27
bugs-and-security is an agent published in the GitHub repository ncoevoet/claude-review-all (25 stars, last pushed 7d ago), licensed MIT. It adds 28 tokens to every session and 1,513 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 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.
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…
performance-engineer
Performance specialist. Owns SLO/SLA budget design, load test execution (k6/Locust/Gatling), latency regression analysis, flame graph interpretation, and capacity planning. Runs after senior-dev, before QA. Writes docs/performance/PERF-{slug}.md. Activated when performance-sla is set in PROJECT.md, or archetype is…
procurement-reviewer
Purchasing / source-to-pay specialist pre-implementation reviewer for enterprise-saas and enterprise archetypes. Outputs threat model TM-procurement-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.