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/tailorau/pact/agents-mdgit clone --depth 1 https://github.com/TailorAU/pactWhat 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 | $0.04024 | $0.04024 |
| Opus 5 | $0.02012 | $0.02012 |
| Sonnet 5 | $0.00805 | $0.00805 |
| Haiku 4.5 | $0.00402 | $0.00402 |
Grade A, and why
pact 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PACT Repo — Agent Onboarding
If you're an AI agent (Claude Code, Cursor, or any framework) opening this repo: read this first.
This is the public spec repo for PACT — Protocol for Agent Contexture and Trust (the backronym was refined from "Consensus and Truth"; the acronym and all pact* identifiers are unchanged; "Contexture and Trust" is normative from v2.1, and shipped v2.0.x stays "Consensus and Truth" as-released per the frozen-version rule below). Vendor-neutral and dual-licensed: software (cli/, mcp/, reference-server/, runner, tools/) is MIT (LICENSE); the specification (spec/**) is under SPEC-LICENSE.md — a royalty-free copyright + patent implementation grant with defensive termination (W3C/MCP/A2A pattern). Neither grants the "PACT" / "PACT Conformant" marks. Implementations live elsewhere; this repo holds the specification, reference CLI, reference MCP server, and a minimal reference server.
Family map (read before confusing PACT with products): docs/PACT_FAMILY.md. PACT is the protocol. .HMAN is the §17 reference impl (local voice enrol — no public register). AINK is money. Sovrgn is the intelligence market (sovrgn.ai/hman is 404). Do not invent a PACT signup.
You are here
TailorAU/pact/
├── spec/v2.0/ ← current stable spec (released 14 May 2026)
│ ├── SPECIFICATION.md
│ ├── resource-types.yaml ← machine-readable resource-type registry (§14.3)
│ ├── schemas/ ← JSON Schema 2020-12, incl. authorization-proof, principal-registry, agent-identity
│ └── conformance/ ← test vectors + @pact-protocol/conformance-runner
├── spec/v2.2/ ← current stable spec (Matter §24; promoted 27 May 2026, not yet tagged v2.2.0 — #33); has ERRATA.md
├── spec/v2.3/ ← DRAFT, not released: v2.2 + §25 consensus / authorization / legal-execution safety boundary (#41)
├── spec/v1.1/ ← previous stable spec; has ERRATA.md
├── cli/ ← @pact-protocol/cli (vendor-neutral coordination CLI; v2.0 — `--authorization-proof`, `pact verify-proof`, `pact profile`)
├── mcp/ ← @pact-protocol/mcp (vendor-neutral MCP for PACT servers; v2.0 — pact_ask, pact_negotiate_*, pact_profile)
├── CHANGELOG.md ← release notes per spec version
├── docs/ ← supplementary architecture / protocol notes
│ ├── v2-plan.yaml ← the PACT v2 roadmap (now mostly DONE)
│ └── v2-prep/ ← v2 working artifacts (decision record, RFC drafts, gap analyses)
├── examples/ ← example payloads and integrations
└── README.md ← public landing
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 · 142 lines · 4,024 tokens per session scan A fc2a1f85df46
pact AGENTS.md is an instructions file published in the GitHub repository TailorAU/pact (2 stars, last pushed 2d ago), licensed MIT. It adds 4,024 tokens to every session, about $0.0201 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 2026-08-31.
Other instructions, from other repositories
claw-consensus AGENTS.md
Instructions for tonydzi/claw-consensus, covering agents.md — working in this repo, what this repo is, stack and layout, how to verify a change and boundaries — what needs a human.
gemot CLAUDE.md
Instructions for justinstimatze/gemot, covering gemot, key commands and architecture.
sprawling AGENTS.md
Instructions for 2youg1/sprawling, covering agents.md — how work is done in this repository, the loop, read before you write, one change, five steps and the rules a machine holds.
sous-chef AGENTS.md
Instructions for tomascupr/sous-chef, covering sous-chef, map and working agreements.
agiwo AGENTS.md
Instructions for xhwSkhizein/agiwo, covering agents.md, how to use this file, truth source order (adr 0048 / 0049), logging and config hot reload.
AI-System-Design-Consultant CLAUDE.md
Instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.