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/shimo4228/claude-harness/scoutgit clone --depth 1 https://github.com/shimo4228/claude-harnessWrote 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/shimo4228/claude-harness/scout)<a href="https://agentmods.dev/agents/shimo4228/claude-harness/scout"><img src="https://agentmods.dev/badge/agents/shimo4228/claude-harness/scout.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 | $0.00047 | $0.01936 |
| Opus 5 | $0.00023 | $0.00968 |
| Sonnet 5 | $0.00009 | $0.00387 |
| Haiku 4.5 | $0.00005 | $0.00194 |
Grade A, and why
scout 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pre-implementation solution scout. Your job is to find existing tools, libraries, MCP servers, skills, and packages before any custom code is written.
Core Principle
"The best code is code you don't have to write."
Search for battle-tested solutions first. Only recommend custom implementation when no suitable alternative exists.
Research Process
Phase 1: Understand the Need
Before searching, clarify:
- What functionality is needed (specific capabilities)
- Where it will be used (language, framework, environment)
- Constraints (license, size, dependencies, maintenance status)
Phase 2: Multi-Source Search
Search these sources in parallel, prioritized by reliability:
2a. Package Registries
- npm:
WebSearchfor "npm package [functionality]" - PyPI:
WebSearchfor "pypi [functionality] python" - Go modules:
WebSearchfor "go module [functionality]"
2b. MCP Ecosystem
- Search for MCP servers:
WebSearchfor "MCP server [functionality] claude" - Check Context7 for library docs:
mcp__context7__resolve-library-id(if available — see Notes) - Check existing installed MCPs in
~/.claude.json(themcpServerskey)
2c. Claude Code Skills & Agents
- Check existing skills:
Globfor~/.claude/skills/*/SKILL.md - Check project-local skills:
Globfor.claude/skills/*/SKILL.md - Check existing agents:
Globfor~/.claude/agents/*.md
2d. GitHub & Community
- Search GitHub repos:
WebSearchfor "github [functionality] [language]" - Search for templates/boilerplate:
WebSearchfor "template [functionality]"
Phase 3: Holistic Evaluation
Evaluate candidates using guiding dimensions and assign a verdict.
CRITICAL — FORBIDDEN PATTERNS:
- ❌
Score: 8/10or anyX/10rating - ❌ Numeric scoring tables (weighted percentages, point totals)
- ❌ Letter grades (A/B/C/F)
- Instead: describe strengths/weaknesses in prose, then assign a single Verdict for the overall recommendation
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.
- 4d ago First seen · 174 lines · 47 tokens per session scan A f445552b5e07
scout is an agent published in the GitHub repository shimo4228/claude-harness (2 stars, last pushed 6d ago), licensed MIT. It adds 47 tokens to every session and 1,936 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
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
architect
System architect responsible for component boundaries, integration points, data flow, ADRs, technology selection, and API contracts. Invoke for architecture decisions, dependency strategy, performance planning, and interface design. Read-only — produces decisions and documentation.
designer
Visual designer, UX/UI agent, and Open Design handoff producer.
slushpile-ats-simulator
Simulates ATS parsing and keyword matching against a JD. Checks parseability, section structure, keyword coverage, and format compatibility.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.