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/dnlbox/ai-protocol/agents-mdgit clone --depth 1 https://github.com/dnlbox/ai-protocolWhat 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 | $0.01370 | $0.01370 |
| Opus 5 | $0.00685 | $0.00685 |
| Sonnet 5 | $0.00274 | $0.00274 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
ai-protocol 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the harness-agnostic contract for AI-assisted work in this repository.
The universal baseline ends at the Project Specifics marker.
The Project Specifics section defines how this repository applies the baseline.
Instruction format
- Write one independently testable instruction per bullet.
- Use the section heading to provide context.
- Put rationale in a separate paragraph.
- Put examples in a separate paragraph.
- Keep each Markdown paragraph on one physical line.
- Keep each Markdown list item on one physical line.
Instruction discovery
- Read the nearest
AGENTS.mdbefore changing files. - Treat the nearest
AGENTS.mdas authoritative for its directory tree. - Load
.agents/roles/leader.mdwhen acting as the primary agent. - Load
.agents/roles/teammate.mdwhen accepting delegated work. - Load
.agents/roles/adjudicator.mdwhen reviewing a disputed or high-consequence decision. - Load a skill only when the user invokes it or its stated trigger applies.
- Load only the project documents relevant to the approved objective.
- Keep harness-specific instruction files as pointers to this contract.
Project truth
- Treat
docs/concept/as accepted product intent. - Treat the Project Specifics section as the repository execution contract.
- Treat
BUILD_STATE.mdas the latest verified repository checkpoint. - Treat executable evidence as authoritative for implemented behaviour.
- Treat a runtime ledger as authoritative only for live worker state.
- Treat conversation history as non-authoritative context.
- Resolve contradictions in favour of the source that owns the disputed fact.
- Surface unresolved authority conflicts to the user.
Approved objectives
- Treat approval of a bounded implementation objective as authorization to complete that objective.
- Plan the approved objective when no adequate plan exists.
- Update the plan when implementation reveals new in-scope work.
- Continue automatically after planning.
- Continue automatically after an internal task completes.
- Ask the user only when a decision would materially change product intent.
- Ask the user only when a decision would materially expand scope.
- Stop when required authority falls outside the approved objective.
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 · 166 lines · 1,370 tokens per session scan A e41229a0e990
ai-protocol AGENTS.md is an instructions file published in the GitHub repository dnlbox/ai-protocol (18 stars, last pushed 23d ago), licensed MIT. It adds 1,370 tokens to every session, about $0.0068 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
semantix CLAUDE.md
Instructions for Gnosil/semantix, covering 项目规则（claude code） and 1. 改动须经用户过目；由 claude 提交到分支 + pr，用户 review 后合并.
mda CLAUDE.md
Instructions for sno-ai/mda, covering claude.md — sno-ai/mda, release process for @markdown-ai/cli, to cut a release (any 1.1.x, 1.2.0, 2.0.0 — same flow), release notes — non-negotiable and what's new.
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
crystal AGENTS.md
Instructions for stravu/crystal, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
conforme AGENTS.md
Instructions for maxgfr/conforme, covering project instructions, claude.md, project overview, build & test and architecture.
conforme GEMINI.md
Instructions for maxgfr/conforme, covering claude.md, project overview, build & test, architecture and keeping docs in sync.