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/os-factory/har/agents-mdgit clone --depth 1 https://github.com/os-factory/harWrote 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/os-factory/har/agents-md)<a href="https://agentmods.dev/instructions/os-factory/har/agents-md"><img src="https://agentmods.dev/badge/instructions/os-factory/har/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 | $0.04798 | $0.04798 |
| Opus 5 | $0.02399 | $0.02399 |
| Sonnet 5 | $0.00960 | $0.00960 |
| Haiku 4.5 | $0.00480 | $0.00480 |
Grade A, and why
har 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 4d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HAR — Agent Development Guide
Guide for coding agents working on this repository (@osfactory/har — the CLI and MCP control plane).
For setup, testing fixtures, and PR workflow, see CONTRIBUTING.md.
This repo dogfoods HAR — .har/ at the repo root defines how coding agents validate changes here.
HAR / agent environment
This repository uses a .har/ harness. It is how you run and verify this
project — launch a slot for live apps, browsers and screenshots; never
hand-roll docker or dev-server startup. If a harness command fails, fix the
harness or report it; do not fall back to ad-hoc commands.
- Launch first —
har_launch_environment/har env launch <id>. Make ALL edits under the returned work dir, never the main checkout. Bind tracker work with--work-id/--work-urlwhen the task names an issue. - Verify before done —
har_run_verification(full: true) /har env verify <id> --full. Commit in the session worktree. - Stop at handoff — report summary, session branch and preview URLs, then
wait. Never autonomously
complete,teardown, push, or open a PR.
Occupied slots always block: complete / teardown, then launch. Customize the
harness only through harness.env, stages.json + .har/stages/, .har/hooks/
and .har/plugins/ — there is no generated .har/*.sh entry-point surface.
Full detail — slot environment, readiness, definition of done, project commands,
commit gate: .har/README.md and .har/stages.json.
Harnesses in this repo
This is a monorepo with three harnesses — pick the one that owns the files you are changing:
| Path | Profile | Runs | Use when changing | Docs |
|---|---|---|---|---|
.har/ |
cli | @osfactory/har (typecheck, build, unit tests, lint) |
src/, packages/, tests/ |
.har/README.md |
control/.har/ |
default | Mission Control (Next.js + SQLite, browser-e2e) | control/ |
control/.har/README.md |
docs/.har/ |
default | Docs / marketing site (Astro + Playwright screenshots) | docs/ |
docs/.har/README.md |
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.
- 4d ago First seen · 292 lines · 4,798 tokens per session scan A 9bf626372db7
har AGENTS.md is an instructions file published in the GitHub repository os-factory/har (83 stars, last pushed 4d ago), licensed Apache-2.0. It adds 4,798 tokens to every session, about $0.0240 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
ctx AGENTS.md
Instructions for agentis-tools/ctx, covering ctx contributor instructions, read before changing the repository, invariants and validation.
ctx CLAUDE.md
Instructions for agentis-tools/ctx, covering claude operating instructions for ctx, ctx-assisted development and project tracking.
alego AGENTS.md
Instructions for singula-ai/alego, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.
alego CLAUDE.md
Instructions for singula-ai/alego, a project described as: Build AI Agents like playing LEGOs. Everything is a Plugin.
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.
coograph brutal-honesty.instructions.md
Global communication style — applies to all workspaces and conversations.