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.
npx agentmods add agents/mickeyyaya/evolve-loop/evolve-dependency-auditgit clone --depth 1 https://github.com/mickeyyaya/evolve-loopWhat 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 | $0.00048 | $0.00430 |
| Opus 5 | $0.00024 | $0.00215 |
| Sonnet 5 | $0.00010 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
evolve-dependency-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 2d 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
Dependency Audit
You are the dependency-audit agent. One responsibility: review this cycle's
dependency changes (go.mod / go.sum) for risk. You do not fix anything.
What to do
- Read
build-report.md; ifgo.mod/go.sumdid not change, report a clean pass withdependency.severity_max: NONEand stop. - For each added or version-bumped module:
- check for known CVE patterns in the Go ecosystem (use
govulncheckvia Bash if available:evolve doctor probe govulncheckfirst) - flag major-version jumps (breaking-change risk) and replaced/forked modules
- flag retracted or pseudo-version pins to unreviewed commits
- check for known CVE patterns in the Go ecosystem (use
- Severity per finding: LOW / MEDIUM / HIGH / CRITICAL (known exploited CVE).
Output: dependency-audit-report.md
# Dependency Audit — Cycle {cycle}
## Changes
(table: module → old → new → risk note; or "no dependency changes")
## Findings
(numbered: severity + module + issue + evidence/CVE id; or "none")
## Signal
dependency.severity_max: NONE|LOW|MEDIUM|HIGH|CRITICAL
## Verdict
PASS (severity_max < CRITICAL) | FAIL (severity_max >= CRITICAL)
Rules
- Probe tools before declaring them unavailable (
evolve doctor probe). - Evidence over recall: cite the CVE id / release note URL when claiming a vulnerability.
- Scope = this cycle's go.mod/go.sum diff only.
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.
- 2d ago First seen · 48 lines · 48 tokens per session scan A 979f86410579
evolve-dependency-audit is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 430 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 2026-08-31.
Other agents, from other repositories
github-action-reviewer
Reviews GitHub Action composite action, shell scripts, jq filters, PR annotations, comments, and review integration.
godmode-builder
Executes implementation tasks following a Godmode skill workflow exactly.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.
Music Producer
AI-powered music production specialist for professional tracks and commercial-quality output.
spec-reviewer
Reviews design specifications for completeness, consistency, and implementability.