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/yourtechbud/coding-harness-config/agents-mdgit clone --depth 1 https://github.com/YourTechBud/coding-harness-configWhat 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 | $0.00775 | $0.00775 |
| Opus 5 | $0.00387 | $0.00387 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
coding-harness-config 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 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding agent configurations
This repo holds the configuration for various coding harnesses like OpenCode, Pi, Claude Code, Codex.
Repo structure
Canonical source
source/skills: Canonical skill assets. Each asset hasasset.yamlfor metadata/frontmatter andbody.mdfor the prompt body.source/commands: Canonical command/prompt assets. OpenCode commands and Pi prompts are generated from here; Claude and Codex receive these as skills with model auto-invocation disabled by default where appropriate.source/agents: Canonical agent/subagent assets.source/harnesses: Handwritten harness config that is copied into generated harness directories.
Generated harness directories
opencode,pi,claude,codex, andisagiare fully generated. Do not edit them directly.- These directories are destructively recreated by
pnpm run generate; make all changes undersource/instead. - Generated outputs are committed so consumers can use the repo without running generation after every pull.
Generation and install commands
pnpm run generate: install each canonical Isagi workflow withpnpm install --frozen-lockfile, then run itstypecheck,test,build, andverifyscripts before recreatingopencode,pi,claude,codex, andisagifromsource/. It then runsnpm installin generated Pi extension folders andpnpm install --frozen-lockfilein generated Isagi workflow folders that contain apackage.json.pnpm run check: verify committed generated outputs matchsource/.pnpm run harness:install: copy generated assets for Codex, OpenCode, Pi, Claude Code, and Isagi into each harness home, overwriting repo-managed destination files.pnpm run harness:clear: remove the currently generated repo-managed files from each harness home.pnpm run harness:sync: run generation once, then install all harnesses.- Per-harness install/clear scripts also exist:
codex:*,opencode:*,pi:*,claude:*, andisagi:*.
After changing canonical assets or generator behavior, suggest that the user run pnpm run generate and pnpm run harness:install so generated outputs and global harness installs are refreshed.
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.
- 2d ago First seen · 50 lines · 775 tokens per session scan A 3859aa7132e7
coding-harness-config AGENTS.md is an instructions file published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 775 tokens to every session, about $0.0039 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
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.
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.