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/peacprotocol/peac/agents-mdgit clone --depth 1 https://github.com/peacprotocol/peacWhat 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 | $0.01155 | $0.01155 |
| Opus 5 | $0.00577 | $0.00577 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
peac 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent-readable metadata for PEAC Protocol. Last reviewed: 2026-06-24
Identity
- Protocol: PEAC (wire formats:
interaction-record+jwt(current),peac-receipt/0.1(frozen legacy)) - Specification: https://www.peacprotocol.org
- Key Discovery:
iss->/.well-known/peac-issuer.json->jwks_uri-> JWKS - Algorithm: EdDSA (Ed25519)
Capabilities
- Receipt Issuance and Verification: Signed receipts (
interaction-record+jwtJWS) for verifiable interaction evidence - Purpose Declaration: Structured intent via
PEAC-Purposeheader - Agent Identity: Proof-of-control binding (see AGENT-IDENTITY.md)
- Policy Discovery: Machine-readable terms at
/.well-known/peac.txt
Proof Methods
| Method | Standard | Description |
|---|---|---|
http-message-signature |
RFC 9421 | HTTP Message Signatures |
dpop |
RFC 9449 | DPoP token binding |
mtls |
RFC 8705 | Mutual TLS client certificate |
jwk-thumbprint |
RFC 7638 | JWK Thumbprint confirmation |
MCP Integration
PEAC receipts attach to MCP tool responses via the Evidence Carrier Contract.
JSON-RPC Response (_meta carrier):
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"content": [...],
"_meta": {
"org.peacprotocol/receipt_ref": "sha256:abc123...",
"org.peacprotocol/receipt_jws": "eyJhbGciOiJFZERTQSIsInR5cCI6ImludGVyYWN0aW9uLXJlY29yZCtqd3QiLC..."
}
}
}
HTTP Transport:
PEAC-Receipt: eyJhbGciOiJFZERTQSIsInR5cCI6ImludGVyYWN0aW9uLXJlY29yZCtqd3QiLC...
The PEAC-Receipt header carries a compact JWS (never a bare receipt_ref).
A2A Agent Card Extension
For A2A (Agent-to-Agent Protocol, Linux Foundation) discovery via /.well-known/agent-card.json:
Agent Card (capabilities.extensions[] array, A2A v1.0.0):
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 · 129 lines · 1,155 tokens per session scan A ca67f636a52b
peac AGENTS.md is an instructions file published in the GitHub repository peacprotocol/peac (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 1,155 tokens to every session, about $0.0058 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
t2000 CLAUDE.md
Instructions for mission69b/t2000, covering claude.md, architecture — the big picture, what this monorepo is (product first), three brands / repos and this repo structure.
hiveconsciousness CLAUDE.md
Claude Code instructions for srotzin/hiveconsciousness, covering instructions, execution rules, repo conventions, core rules and output persistence.
hivegate CLAUDE.md
Claude Code instructions for srotzin/hivegate, covering instructions, execution rules, repo conventions, core rules and output persistence.
innovation-lab-examples general.instructions.md
Instructions for fetchai/innovation-lab-examples, covering general instructions, project context, code quality & formatting, ai assistance and development commands.
innovation-lab-examples typescript.instructions.md
Instructions for fetchai/innovation-lab-examples, a project described as: 80+ production-ready AI agent examples in Python — build autonomous agents, multi-agent systems and agentic AI with uAgents, ASI:One, MCP, A2A, LangChain, CrewAI, Gemini, Claude and OpenAI.
innovation-lab-examples python.instructions.md
Instructions for fetchai/innovation-lab-examples, a project described as: 80+ production-ready AI agent examples in Python — build autonomous agents, multi-agent systems and agentic AI with uAgents, ASI:One, MCP, A2A, LangChain, CrewAI, Gemini, Claude and OpenAI.