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/asimons81/hermes-gpt/agents-mdgit clone --depth 1 https://github.com/asimons81/hermes-gptWrote 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/asimons81/hermes-gpt/agents-md)<a href="https://agentmods.dev/instructions/asimons81/hermes-gpt/agents-md"><img src="https://agentmods.dev/badge/instructions/asimons81/hermes-gpt/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 5.1 | $0.00930 | $0.00930 |
| Opus 5 | $0.00465 | $0.00465 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
hermes-gpt 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 6d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
These instructions apply to the entire hermes-gpt repository.
Start here
Before changing code or documentation:
- Read
docs/README.mdfor the documentation authority map. - Read
pyproject.tomlfor the checked-out package version and shipped modules/docs. - Read the current operational document for the subsystem you are touching.
- Inspect the implementation module and its tests before changing behavioral claims.
Do not treat docs/design/*, docs/releases/*, or FEASIBILITY.md as current runtime instructions. They preserve design and release history.
Source-of-truth precedence
When sources disagree:
- current implementation and tests;
- current operational docs;
- current release notes / CHANGELOG;
- historical design, risk, counsel, release-plan, and feasibility artifacts.
Never change runtime behavior solely to make it match a historical plan. First determine whether the implementation or the documentation is the intended current contract.
Product invariants
Preserve these unless the task explicitly changes the security model and includes corresponding tests/docs:
- local loopback is the default network boundary;
- public unauthenticated Operator hosting is unsupported;
- default behavior is read-only;
- mutating Operator actions are opt-in and dry-run-first;
- direct mutation requires server direct mode plus per-call gates;
- Owner Mode is break-glass and does not bypass secret-path protections;
.env, auth/token stores, SSH/AWS secrets, vault secrets, and secret-looking files remain denied;- protected subprocess paths use fixed argv and
shell=False; - raw prompts are not persisted in Operator audit records;
- Mission Control excludes raw messages, memory bodies, transcripts, request dumps, credentials, and profile-secret bodies;
- Work Contract completion is validated from observed state and fails closed when evidence is missing;
- Swarm orchestration has bounded concurrency/rework and a final human approval gate;
- Codex may review Swarm work but is never an implementation owner.
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.
- 6d ago First seen · 119 lines · 930 tokens per session scan A e9fc7ada41fb
hermes-gpt AGENTS.md is an instructions file published in the GitHub repository asimons81/hermes-gpt (206 stars, last pushed 11d ago), licensed MIT. It adds 930 tokens to every session, about $0.0047 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.