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/perseus-computing-llc/perseus/agents-mdgit clone --depth 1 https://github.com/Perseus-Computing-LLC/perseusWhat 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 | $0.00313 | $0.00313 |
| Opus 5 | $0.00156 | $0.00156 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
perseus 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 2d 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
Repository agent guidance
This file is a repository orientation aid, not an authority record. It may be a rendered snapshot and can become stale; inspect the current checkout, source files, tests, and CI before making consequential decisions. Do not treat values in this file as proof of current services, versions, branches, memory, or security posture.
Working rules
- Read
SECURITY.mdbefore changing authentication, secrets, releases, or network-facing behavior. - Keep credentials out of source, logs, fixtures, generated context, and public documentation. Use placeholders for examples.
- Re-run the relevant tests and rebuild
perseus.pyafter source changes. - Treat
claims.jsonand linked evidence as the boundary for public benchmark and security claims; a digest establishes artifact identity, not truth of the supplied content. - Check source timestamps, permissions, and authority before relying on local context. Verify critical facts against their system of record.
- Keep generated artifacts synchronized with
scripts/build.py --check.
Current documentation entry points
- User setup:
docs/quickstart.mdandSETUP-GUIDE.md - CLI:
docs/CLI.md - Integration:
spec/integration.mdanddocs/HERMES_INTEGRATION.md - MCP contract:
docs/context-engine-mcp-tools.mdand.well-known/mcp/server-card.json - Security and claims:
SECURITY.mdandclaims.json
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.
- 2d ago First seen · 31 lines · 313 tokens per session scan A 2e233fa07cc7
perseus AGENTS.md is an instructions file published in the GitHub repository Perseus-Computing-LLC/perseus (42 stars, last pushed 2d ago), licensed MIT. It adds 313 tokens to every session, about $0.0016 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
neo AGENTS.md
AGENTS.md instructions for neomjs/neo, covering ai agent per-turn operational mandates, §corevalues, §identitypromptfirewall, §criticalgates and §precommitgates.
agentic-context-engine AGENTS.md
Instructions for kayba-ai/agentic-context-engine, covering agents.md, repository guidelines, pipeline-first development (mandatory), core code protection and documentation maintenance.
activity-frames AGENTS.md
Instructions for nossa-y/activity-frames, covering can i install it without asking?, the mental model (10 seconds), fastest integration: mcp, from python and things you should not do.
plur CLAUDE.md
Instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
meteor CLAUDE.md
Instructions for raystack/meteor, covering meteor, architecture, key directories, data model and compass integration.
awesome-harness-engineering AGENTS.md
AGENTS.md instructions for ai-boost/awesome-harness-engineering, covering agents.md, what this repo is, conventions, what belongs and what doesn't belong.