agent-harness CLAUDE.md

agent-harness CLAUDE.md is an instructions file for coding agents from Ghosteken/agent-harness. It costs 953 tokens per session, scanned A, original, MIT.

Project instructions for agent-harness, a collection of coding-agent skills, specialist agents, commands, hooks, documentation, and validation tools. It describes where these parts live and how the project is organized.

In plain words
What is it for?
Use it when navigating agent-harness, adding or editing skills, working with agent personas or commands, and understanding its build and validation files.
Why use it?
It gives contributors and coding agents the project’s structure, roles, conventions, and validation expectations in one place.

Instructions file

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.

agentmods
npx agentmods add instructions/ghosteken/agent-harness/claude-md
Clone the repo
git clone --depth 1 https://github.com/Ghosteken/agent-harness

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 agent-harness CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ghosteken/agent-harness/claude-md.svg)](https://agentmods.dev/instructions/ghosteken/agent-harness/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ghosteken/agent-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/ghosteken/agent-harness/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 953 This file is loaded in full into every session.
When invoked 953 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00953 $0.00953
Opus 5 $0.00477 $0.00477
Sonnet 5 $0.00191 $0.00191
Haiku 4.5 $0.00095 $0.00095

Measured 2d ago against content hash ba9297e82777, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-harness CLAUDE.md 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.

CLAUDE.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-harness

This is the agent-harness project — a production-grade collection of engineering skills and specialist agent personas for AI coding assistants.

Project Structure

skills/            → Curated skills (SKILL.md per directory) exposed to the agent
archive/           → Pre-prune bulk-import skills and tooling, kept but not exposed
agents/            → Specialist agent personas (12 total — see below)
hooks/             → Session lifecycle hooks
.claude/commands/  → Slash commands for Claude Code
commands/          → Slash commands for Antigravity CLI
.gemini/commands/  → Slash commands for Gemini CLI
.claude-plugin/    → Plugin manifest (plugin.json) and marketplace listing
scripts/           → Skill validation (validate-skills.js), agent-scopes.json, install/build scripts
references/        → Supplementary checklists (testing, performance, security, accessibility, orchestration)
docs/              → Setup guides for different tools
CONTRIBUTING.md    → Guidelines for adding or editing skills

Agent Personas

Agent Role Primary Scope
code-reviewer Senior Staff Engineer Five-axis code review
security-auditor Security Engineer Vulnerability detection, OWASP
test-engineer QA Engineer Test strategy, coverage analysis
web-performance-auditor Web Performance Engineer Core Web Vitals audit
api-developer Senior API Engineer REST/GraphQL, spec-first, auth, versioning
db-architect Senior Database Architect Schema design, indexing, migrations
senior-devops Senior DevOps Engineer CI/CD, IaC, containers, GitOps
senior-frontend-engineer Senior Frontend Engineer React/TS, accessibility, Core Web Vitals
senior-cloud-architect Senior Cloud Architect Multi-region, IAM, HA/DR, cost optimisation
senior-backend-engineer Senior Backend Engineer Service architecture, async, queues, caching
ai-ml-engineer AI/ML Engineer Prompt engineering, RAG, LLM evaluation
senior-qa-engineer Senior QA Engineer Feature verification, fix validation, regression checks

Read the full file on GitHub · 68 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. 2d ago Changed · +4 tokens per session ba9297e82777
  2. 5d ago First seen · 68 lines · 949 tokens per session scan A 6ac6e8a90b15

Subscribe to this mod's changes

agent-harness CLAUDE.md is an instructions file published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed yesterday), licensed MIT. It adds 953 tokens to every session, about $0.0048 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.