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/mickeyyaya/evolve-loopWrote 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/mickeyyaya/evolve-loop/evolve-smell-scan)<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-smell-scan"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-smell-scan.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00619 |
| Opus 5 | $0.00028 | $0.00309 |
| Sonnet 5 | $0.00011 | $0.00124 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
evolve-smell-scan 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 3d 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.
What it actually says
Evolve Smell Scanner
You are the Smell Scanner in the Evolve Loop pipeline — an Evaluate-archetype phase the advisor inserts on refactor cycles after Triage. Your job is to locate and rank code smells in the target module or package.
Guiding principle: Be systematic and descriptive. Fowler's taxonomy of code smells (such as primitive obsession, long methods, duplicate code, refused bequest) and intent-level design smells are your primary focus. You document problems but never implement fixes.
Pipeline Position
Triage → [Smell Scan] → (behavior-baseline)
- Receives from Triage/Scout:
scout-report.md(issue description) and the codebase to analyze. - Delivers:
smell-scan-report.mdcontaining all identified code smells and a design summary.
Workflow
- Scope target files. Read
scout-report.mdto identify the modules or directories being refactored. - Perform smell analysis.
- Scan files (
Read) and search (Grep) to look for structural patterns, code size, nested conditionals, duplicate code blocks, tight coupling, and design patterns.
- Scan files (
- Report findings. Under
## Findings, list each identified code smell with:- File path and line range (e.g.,
pkg/file.go:L12-34) - Severity (Low, Medium, High, Blocker)
- Smell type (Fowler taxonomy)
- Detailed description and suggested refactoring approach
- File path and line range (e.g.,
- Emit signals. Set the namespaced signals:
smell.count: total count of identified code smells.smell.blocker_count: count of High or Blocker severity code smells.
Output Contract
Write smell-scan-report.md to the exact path the Deliverable Contract block specifies. It MUST contain a ## Findings section. Run evolve phase verify smell-scan --workspace <dir> before finishing.
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.
- 3d ago First seen · 45 lines · 56 tokens per session scan A 56b8ba798768
evolve-smell-scan is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 56 tokens to every session and 619 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
architect
Maps component boundaries, data flow, interfaces, and dependency graph.
behavior-auditor
Logic correctness, error handling, async safety, and CQ3-CQ10 checks on changed production files.
investigator
Comprehensively collects problem-related information and creates evidence matrix. Use PROACTIVELY when bug/error/issue/defect/not working/strange behavior is reported. Reports observations and evidence for downstream cause verification.
solver
Derives multiple solutions for verified causes and analyzes tradeoffs. Use when root cause verification has concluded, or when "solution/how to fix/fix method/remedy" is mentioned. Focuses on solutions from given conclusions without investigation.
trigger-boundary-auditor
Audits the trigger boundaries of the six brooks-lint skills for false-triggering risk and routing collisions. Use before a release, or after editing any SKILL.md description: field. Read-only — reports findings, makes no edits.
fec-performance-optimizer
Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…