Borrowing it
Nothing to install: this file belongs to nihen/ah. 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/nihen/ah/main/AGENTS.mdgit clone --depth 1 https://github.com/nihen/ahWrote 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/nihen/ah/agents-md)<a href="https://agentmods.dev/instructions/nihen/ah/agents-md"><img src="https://agentmods.dev/badge/instructions/nihen/ah/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/nihen/ah/agents-md"><img src="https://agentmods.dev/badge/instructions/nihen/ah/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 | $0.00400 | $0.00400 |
| Opus 5.5 | $0.00160 | $0.00160 |
| Sonnet 5.5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
ah 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 1mo 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.
What it actually says
ah — Agent History
Cross-agent session search CLI written in Rust. Treat README.md as the source of truth for usage and output specifications.
Build and verification
cargo test
make install
Run targeted tests during development and cargo test before completing changes. Run make install when verifying behavior with the installed CLI. If a change affects search performance, also benchmark representative ah -a log and ah -a -q <query> log commands.
Architecture
cli.rs: clap definitionsagents/: built-in parser plugins and shared helperscollector.rs/pipeline.rs/resolver.rs/search.rs: collection, filtering, resolution, and searchoutput.rs: shared TSV/LTSV/JSON output for log, project, and memoryshow.rs/resume.rs: transcript display and resuming sessions in the original agent
Keep search and parsing in-process. Remote aggregation uses SSH to run ah on the host where the data lives (--remote or -A). Ordinary subcommands filter by the current directory; -a selects all directories. The project subcommand defaults to all directories.
Extending agents
To reuse an existing parser through configuration, use [agents.<name>] in ~/.ahrc. For a new format, add a parser under src/agents/ and register it in src/agents/mod.rs. Follow the existing plugins and the AgentPlugin trait.
Release
Only perform release work when explicitly requested. Create a release/vX.Y.Z branch from the latest origin/main, update the version in Cargo.toml, and open a PR targeting main. After the PR is merged into main, the workflows create the tag and GitHub Release, publish to crates.io, and update the Homebrew tap.
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.
- 1mo ago Changed · -68 lines · -694 tokens per session d2977c1ee55e
- 2mo ago First seen · 99 lines · 1,094 tokens per session scan A fa5ad84cd31f
ah AGENTS.md is an instructions file published in the GitHub repository nihen/ah (9 stars, last pushed 21d ago), licensed MIT. It adds 400 tokens to every session, about $0.0016 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.
ah AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ah AGENTS.mdnihen/ah | Instructions file | 9 | 21d ago | MIT | A | 400 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |