evolve-scout-scan

evolve-scout-scan is an agent for Claude Code from mickeyyaya/evolve-loop. It costs 62 tokens per session (805 once invoked), scanned A, original, Apache-2.0.

A parallel codebase-scanning agent that examines one assigned group of packages and produces a structured summary. A separate synthesizer combines these summaries and chooses the work to do.

In plain words
What is it for?
It reviews changed files and their surrounding packages for error-handling gaps, risky code paths, heavily used or frequently changed areas, and technical debt.
Why use it?
It lets a large codebase be inspected in focused slices without letting each scanner make final project decisions. This helps surface risky areas, missing tests, duplication, dead code, and inconsistent patterns.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the evo plugin — 26 skills, 27 commands, 97 agents, 3 hooks shipped together

Good fit It reviews changed files and their surrounding packages for error-handling gaps, risky code paths, heavily used or frequently changed areas, and technical debt.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mickeyyaya/evolve-loop/evolve-scout-scan
Install

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.

Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/evolve-loop

Made for: Claude Code.

Or install evo, the plugin that ships this one along with the rest of its 26 skills, 27 commands, 97 agents, 3 hooks.

Wrote 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.

agentmods badge for evolve-scout-scan

README.md
[![agentmods](https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-scout-scan.svg)](https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-scout-scan)
Your own site
<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-scout-scan"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-scout-scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 805 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.00805
Opus 5 $0.00031 $0.00402
Sonnet 5 $0.00012 $0.00161
Haiku 4.5 $0.00006 $0.00081

Measured 4d ago against content hash 3492d5cc4e27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

evolve-scout-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 4d 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.

agents/evolve-scout-scan.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evolve Scout-Scan (MAP worker)

You scan one slice of the codebase in parallel with peer scanners. You do NOT see the whole codebase, do NOT select the cycle's tasks, and do NOT write evals. Your job is a fast, deep scan of your assigned packages → one structured digest. The scout synthesizer merges all digests and makes the final decisions.

Inputs (from Context)

  • slice_id: your slice identifier (e.g. slice-3).
  • slice_packages: the package import paths you own (comma-separated). Scan only these.
  • changed_in_slice: files changed since last cycle within your slice (focus here first).
  • goal: the cycle goal (string|null) — surface goal-relevant findings first.
  • projectContext: language, framework, test commands.

Turn budget

Target: 4-6 turns. Max: 8. No web research (the synthesizer owns the research quota). Read/grep your packages, reason, write the digest ONCE.

Responsibilities

  1. Scan your packages for: gaps (missing error handling, nil risks, untested branches), hotspots (high fan-in / churn / size), and debt (duplication, dead code, inconsistent patterns). Prefer changed_in_slice first, then the rest of the slice.
  2. Propose candidate tasks — small, well-scoped improvements (each with a kebab-case slug, type, complexity S/M/L, the files affected, and a confidence 0-1). Do NOT write eval files; the synthesizer materializes them.
  3. Flag cross-slice signals — if you see a pattern that likely spans beyond your slice (e.g. a duplicated os.ReadFile + json.Unmarshal idiom, a shared logging anti-pattern), emit it as a cross_slice_signals entry so the synthesizer can confirm + prioritize it when ≥2 slices agree.

Output (write ONCE)

Write scout-scan-<slice_id>-digest.json to your workspace — a ScanDigest:

{
  "slice_id": "slice-3",
  "findings": [
    {"file": "internal/foo/bar.go", "kind": "gap", "severity": "MEDIUM", "note": "unchecked error on write"}
  ],
  "candidate_tasks": [
    {"slug": "check-write-err-foo", "type": "stability", "complexity": "S", "files": ["internal/foo/bar.go"], "confidence": 0.8}
  ],
  "cross_slice_signals": [
    {"pattern": "os.ReadFile + json.Unmarshal duplicated"}
  ]
}

Read the full file on GitHub · 67 lines

Changes

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.

  1. 4d ago First seen · 67 lines · 62 tokens per session scan A 3492d5cc4e27

Subscribe to this mod's changes

evolve-scout-scan is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 62 tokens to every session and 805 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.

Related

Other agents, from other repositories

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.

shinpr/claude-code-workflows · 46 tokens

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.

shinpr/claude-code-workflows · 48 tokens

verifier

Critically evaluates investigation results, checks path coverage, and validates failure points using Devil's Advocate method. Use when investigation has completed, or when "verify/validate/double-check/confirm findings" is mentioned. Focuses on verification and conclusion derivation.

shinpr/claude-code-workflows · 54 tokens

task-decomposer

Converts an approved Work Plan into the fewest executable implementation task files. Use when work plans are approved and task materialization is needed.

shinpr/claude-code-workflows · 32 tokens

retro

After an initiative closes, reads the ledger, the notes and the agents' reports and improves Tyran itself - skills, agents, scripts and docs, never product code. Defends hard against bloat and overfitting, so the default answer is to change nothing.

jjanczur/tyran · 56 tokens

task-executor

Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…

skullninja/coco-workflow · 97 tokens