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/myshkin451/vibe-harness/agents-mdgit clone --depth 1 https://github.com/myshkin451/vibe-harnessWhat 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 | $0.00318 | $0.00318 |
| Opus 5 | $0.00159 | $0.00159 |
| Sonnet 5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
vibe-harness AGENTS.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 yesterday.
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
Vibe Harness Repository Guide
Start Here
- Main skill:
skills/vibe-harness/SKILL.md - Source-of-truth docs:
docs/index.md - Current state board:
progress.md - Detailed skill references:
skills/vibe-harness/references/ - Copyable templates:
skills/vibe-harness/assets/templates/ - Repo validation:
scripts/validate.py - Audit script:
scripts/audit.py - Launch guidance:
docs/launch-playbook.md
Project Goal
Vibe Harness turns a human project plan into a lightweight agent-ready repository harness for sustainable AI coding.
Working Rules
- Keep the skill body concise; move deeper guidance to
skills/vibe-harness/references/. - Keep templates generic, small, and easy to adapt.
- Do not add heavyweight governance artifacts unless they solve a clear continuity or verification problem.
- Prefer concrete paths, commands, and evidence over broad agent philosophy.
- Do not make unverified adoption, benchmark, or compatibility claims.
Validation
Run before finishing changes:
python3 scripts/validate.py
python3 scripts/audit.py examples/expected-harness
If validation cannot run, explain why and record the likely impact.
Release Shape
The repo should stay installable as a skill package and understandable as an open-source project. README is for users; skills/vibe-harness/SKILL.md is for agents; docs/launch-playbook.md is for maintainers preparing public launch.
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.
- yesterday First seen · 40 lines · 318 tokens per session scan A c9abb5ab220e
vibe-harness AGENTS.md is an instructions file published in the GitHub repository myshkin451/vibe-harness (1 stars, last pushed 3mo ago), licensed MIT. It adds 318 tokens to every session, about $0.0016 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 instructions, from other repositories
rust-faf-mcp AGENTS.md
Instructions for Wolfe-Jam/rust-faf-mcp, covering agents.md — rust-faf-mcp, setup & build, run the tests, where things live and architecture (load-bearing).
rust-faf-mcp CLAUDE.md
Instructions for Wolfe-Jam/rust-faf-mcp, covering claude.md - rust-faf-mcp and project: rust-faf-mcp.
bun-sticky-faf CLAUDE.md
Instructions for Wolfe-Jam/bun-sticky-faf, covering claude.md — bun-sticky, what this is, stack, context and bun-sticky.
yggdrasil AGENTS.md
Instructions for luizfelipedm/yggdrasil, covering agents.md — working on the kit itself, what ships where, invariants — do not "clean these up", asymmetries that are deliberate and before you commit.
solid-ai-templates CLAUDE.md
Claude Code instructions for braboj/solid-ai-templates, covering solid-ai-templates, 1. project, 1.1 overview, 1.2 architecture and 1.3 commands.
agent-rulescope AGENTS.md
AGENTS.md instructions for 13624725933/agent-rulescope, a project described as: See exactly which instructions your coding agent inherits. Scan AGENTS.md, CLAUDE.md, Cursor and Copilot rules.