Borrowing it
Nothing to install: this file belongs to hermes-labs-ai/hermeneutic. 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/hermes-labs-ai/hermeneutic/main/AGENTS.mdgit clone --depth 1 https://github.com/hermes-labs-ai/hermeneuticWrote 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/hermes-labs-ai/hermeneutic/agents-md)<a href="https://agentmods.dev/instructions/hermes-labs-ai/hermeneutic/agents-md"><img src="https://agentmods.dev/badge/instructions/hermes-labs-ai/hermeneutic/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/hermes-labs-ai/hermeneutic/agents-md"><img src="https://agentmods.dev/badge/instructions/hermes-labs-ai/hermeneutic/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 | $0.01312 | $0.01312 |
| Opus 5.5 | $0.00525 | $0.00525 |
| Sonnet 5.5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
hermeneutic 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 13d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — using hermeneutic from a coding agent
This file is for AI coding agents and host applications that want to call the
standalone hermeneutic CLI or Python library.
Priority order
Apply these priorities in order when using or extending the package:
- Honor the user's requested scope and protect private correction data.
- Preserve the deterministic, zero-LLM gate and its existing English behavior. Language adapters map vocabulary into that gate; synthetic fixtures cannot establish real-language coverage or authorize a change to canonical rules.
- Validate the requested behavior in the owning checkout before claiming it works. Report tests, host-adapter mechanics, and live delivery separately.
What this tool does
Hermeneutic preserves correction episodes and scoped lessons for later agent
tasks. By default, learn derives a source-verbatim candidate and task cue from
the original episode; inspect it with lessons and activate it with confirm.
An explicit user/host interpretation is optional. context retrieves bounded,
attributed candidate context from task cues and an exact scope. Check
applicability and current instructions before acting. revoke disables a lesson. These commands
do not infer a lesson with a hidden model, install a hook, or rewrite a prompt
automatically. Keep stores private and paths explicit.
The separate output plane is a fixed deterministic English draft check. It flags eight surface shapes including completion overclaiming, relayed authority, unhedged certainty, scope expansion, and unsupported quality adjectives. It does not read the personal correction corpus or run the optional Router.
The host-neutral workflow is: retrieve attributed context, check its scope,
perform the task, then optionally check the output with gate --json or
check_draft. A clean gate result is not evidence of successful lesson transfer.
When to invoke it
Run hermeneutic gate on any assistant draft before you send it to the user
when:
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.
- 13d ago Changed · +17 lines · +244 tokens per session ed9b50653daa
- 24d ago Changed · +13 lines · +135 tokens per session 978f93e2dc12
- 1mo ago Changed · +20 lines · +193 tokens per session 2901b7c37d89
- 2mo ago First seen · 85 lines · 740 tokens per session scan A 3eaccda84f2c
hermeneutic AGENTS.md is an instructions file published in the GitHub repository hermes-labs-ai/hermeneutic (9 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,312 tokens to every session, about $0.0052 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.
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).
generative-ai-for-beginners AGENTS.md
AGENTS.md instructions for microsoft/generative-ai-for-beginners, covering agents.md, project overview, setup commands, initial repository setup and clone the repository.