Borrowing it
Nothing to install: this file belongs to phenomenoner/hermes-agent-harness-plus. 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/phenomenoner/hermes-agent-harness-plus/main/CLAUDE.mdgit clone --depth 1 https://github.com/phenomenoner/hermes-agent-harness-plusWrote 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/phenomenoner/hermes-agent-harness-plus/claude-md)<a href="https://agentmods.dev/instructions/phenomenoner/hermes-agent-harness-plus/claude-md"><img src="https://agentmods.dev/badge/instructions/phenomenoner/hermes-agent-harness-plus/claude-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 | $0.00509 | $0.00509 |
| Opus 5 | $0.00254 | $0.00254 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
hermes-agent-harness-plus CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s "https://phenomenoner.github.io/hermes-agent-harness-plus/?cb=$RANDOM"`. How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for AI agents working in this repository.
What this repo is
A companion toolbox for Hermes Agent:
Task Canvas evidence trails (packages/context-canvas/), archived Autopilot
source, the Prime Agent minion bridge (plugins/), local Qdrant recall helpers
(scripts/), Hermes skills (skills/), and ops checklists (ops-rules/).
Hermes Agent itself is never modified; every piece is optional and documents
its data path and failure posture. Local observability helpers may fail open;
credential, route, ownership, and replay boundaries fail closed.
Before touching README, docs/, or the website
Read ops-rules/docs-and-website-update-guide.md first. It is the single
source of truth for brand voice, color tokens, section anatomy, the content
sync map, and the verification checklist. Non-negotiables:
docs/index.htmlstays a single self-contained file (no external assets, fonts, or analytics) and keeps itsprefers-reduced-motionand:focus-visibleaccessibility blocks.- Honest marketing only: no invented numbers, testimonials, or claims.
- The same quick-start commands must appear identically in
docs/install.md,README.md, and the website#quickstartblocks (visible text anddata-copyattributes). - Website links to
.mdfiles use GitHub blob URLs, never raw relative paths.
Commands
python -m pip install -e '.[mcp]' pytest # install for development
python -m pytest -q # smoke tests (must pass before push)
Deployment
GitHub Pages serves main branch /docs automatically — pushing to main is
the deploy. Verify after ~1–2 minutes with a cache-busted fetch:
curl -s "https://phenomenoner.github.io/hermes-agent-harness-plus/?cb=$RANDOM".
Conventions
- Commits:
docs:/feat:/fix:prefix, imperative subject ≤ 72 chars. - Anything public must pass
ops-rules/public-release-checklist.md— no secrets, no machine-specific paths, placeholders documented. - New third-party dependencies get a source + version + license entry in
NOTICE.
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.
- 8d ago First seen · 50 lines · 509 tokens per session scan A f3aa558538bd
hermes-agent-harness-plus CLAUDE.md is an instructions file published in the GitHub repository phenomenoner/hermes-agent-harness-plus (2 stars, last pushed 4d ago), licensed MIT. It adds 509 tokens to every session, about $0.0025 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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 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).
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.
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.