Borrowing it
Nothing to install: this file belongs to kingassune/harness-starter-pack. 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/kingassune/harness-starter-pack/main/AGENTS.mdgit clone --depth 1 https://github.com/kingassune/harness-starter-packWrote 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/kingassune/harness-starter-pack/agents-md)<a href="https://agentmods.dev/instructions/kingassune/harness-starter-pack/agents-md"><img src="https://agentmods.dev/badge/instructions/kingassune/harness-starter-pack/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/kingassune/harness-starter-pack/agents-md"><img src="https://agentmods.dev/badge/instructions/kingassune/harness-starter-pack/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 | $0.00770 | $0.00770 |
| Opus 5.5 | $0.00308 | $0.00308 |
| Sonnet 5.5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
harness-starter-pack 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 2mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project-level operating instructions for any AI agent working in this repo. Keep this file SHORT, STABLE, and HIGH-SIGNAL. It is loaded into the system prompt and survives context compaction — so put the rules here that must never be forgotten, not things the agent can discover by reading code.
Rule of thumb: if losing a line mid-task would cause a bug, it belongs here. If the agent could figure it out from the codebase, leave it out.
1. What this project is
- Product:
- Primary language / runtime:
- Package manager:
- Where the entrypoint lives:
2. How to work here (the loop)
The agent must follow this cycle on every task:
- Read
PLAN.md(if present) before doing anything. If absent, create one. - Plan — write/update milestones in
PLAN.mdbefore writing code. - Act — make the smallest change that advances the current milestone.
- Verify — run the verification command below after every change.
- Record — append decisions and deviations to
IMPLEMENT.md. - Repeat until all milestones are
[x].
3. Commands
| Action | Command |
|---|---|
| Install deps | … |
| Run / dev server | … |
| Verify (tests) | … ← run after every change |
| Lint / format | … |
| Typecheck | … |
| Build | … |
Verification is mandatory. A change is not complete until the verify command passes. Emit only summary lines to context; log full output to a file.
4. Conventions
- Code style:
- Naming:
- File layout / where things go:
- Tests live in:
- Commit message format:
- Do NOT touch:
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.
- 2mo ago First seen · 84 lines · 770 tokens per session scan A fed982b9aaa0
harness-starter-pack AGENTS.md is an instructions file published in the GitHub repository kingassune/harness-starter-pack (2 stars, last pushed 4mo ago), licensed CC0-1.0. It adds 770 tokens to every session, about $0.0031 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 2026-08-31.
harness-starter-pack AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| harness-starter-pack AGENTS.mdkingassune/harness-starter-pack | Instructions file | 2 | 4mo ago | CC0-1.0 | A | 770 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |