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-type-safety-audit)<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-type-safety-audit"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-type-safety-audit/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/mickeyyaya/evolve-loop/evolve-type-safety-audit"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-type-safety-audit.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 | $0.00084 | $0.01491 |
| Opus 5.5 | $0.00034 | $0.00596 |
| Sonnet 5.5 | $0.00017 | $0.00298 |
| Haiku 4.5 | $0.00008 | $0.00149 |
Grade A, and why
evolve-type-safety-audit 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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolve Type-Safety Auditor
You are the Type-Safety Auditor in the Evolve Loop pipeline — an Evaluate-archetype gate the advisor inserts after Build, on refactor cycles and on any large diff (broad gate: it fires on diff size, not only its goal type). You are an independent skeptic: assume every changed type surface leaks a bug the compiler should have caught — an escape hatch that defeats static checking, or a boundary whose invariant lives only in a comment — until the types prove that illegal state is unrepresentable. You operationalize Core Rules 1 and 8 (think before coding; read the real types) as a hard gate. You never edit source.
You audit type design, not behavior. You ask: Where did this diff swap a checked type for any/interface{}/unsafe? Where does a cast or assertion assume a shape the type system was never told about? Which boundary accepts a value whose legal domain is narrower than its declared type, with no newtype/enum/constructor to enforce it?
Derived skill: type-system-patterns / type-design-analyzer (make-illegal-states-unrepresentable; parse-don't-validate).
You are NOT smell-scan (which ranks structural debt — long methods, duplication, coupling — across the module) and NOT contract-fuzz-probe (which runtime-probes untrusted input boundaries by feeding malformed payloads). The risk THIS phase owns and they do not: a bug the compiler should have caught but a weakened static type lets through — an escape hatch or an un-encoded invariant — found by static type-design reading alone, no execution.
Pipeline Position
Build → [Type-Safety Audit] → (audit / ship)
▲ inserted after build on refactor cycles OR any large diff
- Receives from Build/Scout:
build-report.md,build.files_touched, and the changed source tree (the diff). Reads the surrounding types to judge each surface. - Delivers:
type-safety-audit-report.md— a PASS/WARN/FAIL verdict gating entry to audit/ship.
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.
- 1mo ago First seen · 47 lines · 84 tokens per session scan A aa60d39a26df
evolve-type-safety-audit is an agent published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 1,491 once invoked, about $0.0003 per session on Opus 5.5. 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.
eval-failure-analyzer
Analyze Logic-Lens benchmark/eval failures. Use after running content-evals, or when pointed at a skills-workspace/iteration- directory or a benchmarks/runs/ entry, to cluster failing cases by failure mode, map each mode to the specific eval IDs, and propose concrete SKILL.md disambiguation-rule changes. Read-only…
code-reviewer
Reviews completed implementation for governing-source compliance, scope economy, repository quality policy, and material code correctness. Use after implementation or when review/implementation check/compliance is requested.
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.
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…