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/aeoess/agent-passport-system/agents-mdgit clone --depth 1 https://github.com/aeoess/agent-passport-systemWrote 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/aeoess/agent-passport-system/agents-md)<a href="https://agentmods.dev/instructions/aeoess/agent-passport-system/agents-md"><img src="https://agentmods.dev/badge/instructions/aeoess/agent-passport-system/agents-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 | $0.00852 | $0.00852 |
| Opus 5 | $0.00426 | $0.00426 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
agent-passport-system 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Context and instructions for AI coding agents working on agent-passport-system.
This repo is the public protocol layer. The private gateway product lives in a separate repo. Product intelligence (analytics, compliance automation, drift detection, cross-tenant orchestration, metering) does not belong here.
Dev environment
- Node.js >= 18
npm install- TypeScript strict.
tsc --noUnusedLocals,tsc --noImplicitAnymust pass. - All code under
src/is source of truth;dist/is generated bynpm run build, do not edit.
Test before you ship
npm testruns the full suite, must exit 0 with zero failures before any commit that touchessrc/.npm run test:interopruns the cross-implementation interop suite (SDK + MCP).npm run test:quickis a fast subset for iterative development.- New primitives require new tests. Existing tests do not change unless the spec changes.
PR instructions
- Title format:
<type>(<scope>): <summary>per Conventional Commits. Examples:feat(v2/delegation): add policy-context binding,fix(canonicalization): stable key ordering in JCS helper. - Never merge your own PR. Never push directly to
main. - Version bumps to
package.jsonare a human decision, not an agent decision. Open a PR proposing the bump, leave the merge to a human. - Breaking changes require a major-version bump AND a migration note in
MIGRATION.md. - Run
npm testANDnpm run buildbefore any commit. If the tree is not green, the commit is not ready.
Code style
- No
any. Useunknownwith type narrowing if the shape is genuinely unknown. - Ed25519 for all signatures. No ES256 unless a spec requires it.
- Canonicalization is RFC 8785 JCS + SHA-256, no exceptions. Helper lives at
src/canonicalization/. - Every exported symbol has a JSDoc block describing invariants, not just types.
- No
console.login committed code. Use the structured logger undersrc/logger/.
What this repo is and is not
This repo IS:
- The protocol primitives (identity, delegation, enforcement, governance, commerce, data lifecycle, coordination).
- The types and interfaces that define how APS-compatible systems interoperate.
- Reference test vectors for cross-implementation conformance.
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 Changed · -9 tokens per session d1a162d0c6c3
- 6d ago First seen · 62 lines · 861 tokens per session scan A c3082e33d87d
agent-passport-system AGENTS.md is an instructions file published in the GitHub repository aeoess/agent-passport-system (43 stars, last pushed yesterday), licensed Apache-2.0. It adds 852 tokens to every session, about $0.0043 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
agent-passport-mcp AGENTS.md
AGENTS.md instructions for aeoess/agent-passport-mcp, covering agents.md, about this project, dev environment, test before you ship and pr instructions.
agent-passport-mcp CLAUDE.md
Claude Code instructions for aeoess/agent-passport-mcp: This file exists so Claude Code picks up repo context on startup.
haldir AGENTS.md
Instructions for ExposureGuard/haldir, covering agents.md, what this project is, run + build commands, where things live and conventions.
agent-governance-toolkit copilot-instructions.md
Copilot instructions for microsoft/agent-governance-toolkit, covering copilot instructions for agent-governance-toolkit, architecture, build, test, and lint, python and install (editable, all extras).
FrameCode-VibeWork AGENTS.md
AGENTS.md instructions for Sistema2D/FrameCode-VibeWork, covering agents.md, instruction order, reading-trigger rule, regression rule and when a plan is required.
agent-universe AGENTS.md
AGENTS.md instructions for SunrisesIllNeverSee/agent-universe, covering project state, original goal, architecture at a glance, what is built and functional and what is stubbed.