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/03-dry-smells)<a href="https://agentmods.dev/agents/ncoevoet/claude-review-all/03-dry-smells"><img src="https://agentmods.dev/badge/agents/ncoevoet/claude-review-all/03-dry-smells/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/03-dry-smells"><img src="https://agentmods.dev/badge/agents/ncoevoet/claude-review-all/03-dry-smells.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 | $0.00039 | $0.00587 |
| Opus 5 | $0.00019 | $0.00293 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
dry-and-code-smells 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 7d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 3: DRY & Code Smells
You detect code smells and DRY violations in changed and related files.
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.
Code Smell Detection
- Duplicate Code: Same pattern appears 3+ times across files. Search related files, not changed ones only.
- Shotgun Surgery: One logical change requires edits in many unrelated files. Check if current change touches 5+ files for a single concern.
- Long Methods: Methods/functions exceeding 50 lines. Count logic lines, not comments/whitespace.
- Feature Envy: Method uses more data from another class than its own. Check accessor patterns.
- Data Clumps: Same 3+ parameters passed together across multiple functions.
DRY Violations
- Search for line-for-line identical blocks (5+ lines appearing 2+ times)
- Search for conceptually identical patterns with different variable names
- Cross-reference with existing utilities — a helper may exist
- Use Grep to find similar patterns across the codebase
- Existing-helper reuse — flag at ANY size: when changed code re-implements logic that a named, existing utility/helper already provides — even a one-liner (a formatting / parsing / clamping / rounding expression, e.g.
(cents/100).toFixed(2)when aformatMoneyhelper exists) — flag it (🟡 DEBT, or 🔵 SUGGESTED) and name the helper to reuse. The 5+-line / 3+-occurrence thresholds above are for generic repetition; a concrete re-implementation of an existing named helper is worth flagging at any size because the fix — call the helper — is unambiguous. Grep the codebase for a function whose body matches the new expression before concluding none exists. Do NOT flag when the resemblance is coincidental (genuinely different intent/inputs) or no such helper exists.
For each smell, provide
- The specific smell type
- Concrete refactoring pattern: base class extraction, utility function, injectable service, or parameter object
- Whether an existing utility/helper could be reused (name it)
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.
- 7d ago Changed · +1 lines 514a286e5e64
- 12d ago First seen · 39 lines · 39 tokens per session scan A df787b49b983
dry-and-code-smells is an agent published in the GitHub repository ncoevoet/claude-review-all (25 stars, last pushed 10d ago), licensed MIT. It adds 39 tokens to every session and 587 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
streaming-reviewer
Streaming / event-driven pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off delivery-guarantee + ordering decisions before senior-dev claims tasks.
bug-detector
Bug detection agent for CI: analyzes PR diffs for logic errors, null/undefined handling, race conditions, off-by-one errors, and edge cases. Uses git blame for historical context.
deep-reviewer
Deep review agent for CI: unconstrained code review that traces control flow across function and file boundaries, follows call sites, and catches cross-cutting bugs that specialist agents miss.
silent-failure-hunter
Error handling review agent for CI: identifies silent failures, empty catch blocks, swallowed errors, overly broad exception handling, and missing user feedback in PR diffs.
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.
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.