Borrowing it
Nothing to install: this file belongs to harness/harness-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/harness/harness-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/harness/harness-skillsWrote 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/harness/harness-skills/agents-md)<a href="https://agentmods.dev/instructions/harness/harness-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/harness/harness-skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/harness/harness-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/harness/harness-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.03679 | $0.03679 |
| Opus 5.5 | $0.01472 | $0.01472 |
| Sonnet 5.5 | $0.00736 | $0.00736 |
| Haiku 4.5 | $0.00368 | $0.00368 |
Grade A, and why
harness-skills 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Skills
Scope: This file configures agents working in this repository and agents that load it from a clone. Plugin installs (Claude Code, Cursor, Codex) and npx skills add installs never load it, so runtime rules a skill needs must live in the skill or in a shared file it links (for example references/fme/).
This repository contains model-agnostic workflow instructions for AI coding tools working with Harness.io. Most skills use Harness MCP; FME skills also support the Harness CLI for the operations explicitly listed in their Tools tables.
For FME, load the selected SKILL.md, its applicable local references, and references/fme/tool-map.md plus concepts.md; load write-safety.md before writes. Keep shared references accessible when installing/copying skills. Follow the tool map's capability limits and handoff contract: a slash-skill name means read its linked workflow, not assume a model-specific invocation tool. Unsupported operations stop rather than falling back to guessed commands.
Harness MCP Server
The Harness MCP server provides the generic tools below. CLI-only FME sessions use the verified equivalents in references/fme/tool-map.md; other skills retain their declared MCP requirements:
| Tool | Purpose |
|---|---|
harness_list |
List resources with filters and pagination |
harness_get |
Get a single resource by ID |
harness_create |
Create a resource (requires confirmation) |
harness_update |
Update a resource (requires confirmation) |
harness_delete |
Delete a resource (requires confirmation) |
harness_execute |
Run, retry, interrupt, sync, toggle, approve, reject, test_connection |
harness_search |
Cross-resource keyword search |
harness_describe |
Local metadata/schema lookup (no API call) |
harness_diagnose |
Pipeline failure analysis |
harness_status |
Project health overview |
Tools accept a resource_type parameter (e.g., pipeline, secret, template) to target specific Harness resources. Tools also support Harness UI URL auto-extraction for org_id, project_id, resource_type, and resource_id.
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 Changed · +9 lines · +87 tokens per session 6493b106c223
- 11d ago Changed · +37 lines · +465 tokens per session 8025fda5862f
- 19d ago Changed · +15 lines · +475 tokens per session 398824bc7723
- 20d ago Changed · +2 lines · +47 tokens per session 42bb7cd55537
- 1mo ago Changed · +1 lines · +28 tokens per session 11dbc22c7f82
- 1mo ago First seen · 186 lines · 2,577 tokens per session scan A 55ccb8fcac4f
harness-skills AGENTS.md is an instructions file published in the GitHub repository harness/harness-skills (125 stars, last pushed 2d ago), licensed Apache-2.0. It adds 3,679 tokens to every session, about $0.0147 per session on Opus 5.5. 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).
next.js AGENTS.md
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, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.