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/luisfelipemoro/harness-devkit/agents-mdgit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWrote 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/luisfelipemoro/harness-devkit/agents-md)<a href="https://agentmods.dev/instructions/luisfelipemoro/harness-devkit/agents-md"><img src="https://agentmods.dev/badge/instructions/luisfelipemoro/harness-devkit/agents-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 | $0.00586 | $0.00586 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
Harness-devkit 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 3d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-devkit — Agent Instructions
This repo is the claude-devkit — a multi-plugin skill/agent library originally built for Claude Code. If you are Codex CLI, or another harness reading this file, working in this repo: the canonical engineering standards live in a single place to avoid drift —
Read plugins/coding-pipeline/CLAUDE.md before making any change. It covers coding discipline,
quality gates, security defaults, and per-language rules that apply regardless of which
harness you are.
Two conventions there are easy to get wrong and worth calling out up front:
- Tests are written after the implementation, against a spec frozen before it — then falsified (break the code path, confirm the test fails on its own assertion, restore). Not TDD. A tautological or unfalsified test blocks handoff regardless of coverage. The one exception is a bug fix, which keeps its RED reproduction test.
- Pipeline runs are deliveries: a keyed plan file under
docs/deliveries/, onegit worktreeper delivery on arelease/{slug}-{key}branch, and never a commit or merge tomain— the terminal step is a PR. Seeplugins/coding-pipeline/references/delivery-and-worktree.md.
Harness-specific notes
- Skills (
plugins/*/skills/*/SKILL.md) use onlyname:/description:frontmatter — this is the same shape Codex's own Skills convention expects, so they are directly usable once placed under a.agents/skills/directory Codex scans (repo, user, or system level). Seeplugins/coding-pipeline/scripts/install-codex.shto install them for Codex. - Agents (
plugins/coding-pipeline/agents/*.md) are Claude Code Task-tool subagent definitions (tools:/model:frontmatter, dispatched by name from pipeline skills). Codex has its own declarative subagent format (~/.codex/agents/<name>.toml) — runplugins/coding-pipeline/scripts/generate-codex-agents.shto generate one per persona, with reasoning effort mapped from the Claudemodel:tier. Seeplugins/coding-pipeline/codex/harness-adapter.mdfor the current mapping and known gaps (pipeline sequencing is not yet validated in a live Codex session). - Git hooks (
plugins/coding-pipeline/git-hooks/) are plain POSIX shell and work under any harness or none at all — install viabash plugins/coding-pipeline/scripts/install-git-hooks.sh.
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.
- 3d ago First seen · 37 lines · 586 tokens per session scan A 642f14b9ce55
Harness-devkit AGENTS.md is an instructions file published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 4d ago), licensed MIT. It adds 586 tokens to every session, about $0.0029 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
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.
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.
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).
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.