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 instructions/twaldin/harness/claude-mdgit clone --depth 1 https://github.com/twaldin/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/instructions/twaldin/harness/claude-md)<a href="https://agentmods.dev/instructions/twaldin/harness/claude-md"><img src="https://agentmods.dev/badge/instructions/twaldin/harness/claude-md.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 | $0.01704 | $0.01704 |
| Opus 5 | $0.00852 | $0.00852 |
| Sonnet 5 | $0.00341 | $0.00341 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
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 5d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
harness
harness is a dual-language (Python + TypeScript) adapter library that wraps thirteen
AI coding-agent CLIs — claude-code, openclaude, opencode, codex, gemini,
aider, swe-agent, qwen, continue-cli, pi, factory-droid, kilo, crush —
behind a single uniform RunSpec → RunResult contract. Both implementations sit in
this monorepo and ship in lockstep so any consumer (hone, agentelo, flt, etc.)
gets identical behavior whether it calls harness (Python) or @twaldin/harness-ts.
Authoritative references in this repo:
- SPEC.md — the cross-language contract. Public API, types, error rules.
- ADAPTER-MATRIX.md — per-CLI flags, cost reporting, output shapes.
- CONTRIBUTING.md — code conventions and the "add an adapter" guide.
Repository layout
harness/
├── SPEC.md cross-language contract (THE source of truth)
├── ADAPTER-MATRIX.md per-adapter quirk reference
├── tests/fixtures/*.json shared golden fixtures (Py + TS both consume)
├── src/harness/ Python implementation (see src/harness/CLAUDE.md)
│ ├── base.py RunSpec / RunResult / Adapter dataclasses
│ ├── registry.py run / list_adapters / get_adapter
│ ├── cli.py Typer CLI entrypoint (harness.cli:app)
│ ├── model_normalization.py per-harness canonical model resolution
│ ├── pricing.py cost derivation from token counts
│ ├── _subproc.py subprocess runner + instructions writer
│ └── adapters/ 13 adapter modules, one per CLI
├── ts/ TypeScript implementation (see ts/CLAUDE.md)
│ ├── package.json @twaldin/harness-ts (Bun build + test)
│ ├── src/base.ts mirror of Python base.py types
│ ├── src/registry.ts mirror of Python registry.py
│ ├── src/model-normalization.ts
│ ├── src/pricing.ts
│ ├── src/subproc.ts
│ ├── src/util.ts
│ └── src/adapters/ 13 adapter modules, one per CLI
├── tests/ pytest suite (Python)
└── ts/tests/ bun test suite (TypeScript)
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.
- 5d ago First seen · 136 lines · 1,704 tokens per session scan A dd36d206e335
harness CLAUDE.md is an instructions file published in the GitHub repository twaldin/harness (22 stars, last pushed 1mo ago), licensed MIT. It adds 1,704 tokens to every session, about $0.0085 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.