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/rjmurillo/ai-agents/governancegit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/governance)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/governance"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/governance.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 | $0.00463 | $0.00463 |
| Opus 5 | $0.00231 | $0.00231 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
ai-agents governance.instructions.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 yesterday.
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
Governance File Rules
Files under .agents/governance/ define the rules that bind every other agent role. Changes here have system-wide reach.
MUST
- Human approval. Changes MUST be reviewed and approved by a human maintainer. Auto-merge is prohibited for governance files.
- ADR required. Significant governance changes (new rules, policy reversals, removed constraints) MUST be accompanied by an Architecture Decision Record in
.agents/architecture/. - Consensus for cross-role rules. Changes that affect multiple agent roles MUST follow the consensus protocol in
CONSENSUS.md(domain-weighted voting; security gets 2.0x on security decisions). - Evidence required. Every added or changed normative line under
.agents/governance/MUST have one nearby evidence anchor in the same section: aSource:line, aRefsissue or PR, an ADR link, a retrospective link, or aWhy:paragraph. Reviewers verify this withgit diff -U3 -- .agents/governance/. - No unilateral changes. A single specialist agent MUST NOT alter rules that govern other agents without consensus.
SHOULD
- Update canonical sources first.
PROJECT-CONSTRAINTS.mdis the index of record. New constraints SHOULD land there, with details in a dedicated governance file. - Cross-link. SHOULD link new governance content from
AGENTS.mdandCLAUDE.mdwhen it affects agent defaults. - RFC 2119. Rules SHOULD use MUST / SHOULD / MAY to state requirement strength explicitly.
MUST NOT
- MUST NOT reduce security or review requirements without a unanimous-consensus ADR.
- MUST NOT remove the evidence link for an existing rule. Supersession requires a new ADR, not silent deletion.
References
.agents/governance/PROJECT-CONSTRAINTS.md. Canonical constraints index.agents/governance/CONSENSUS.md. Consensus algorithms and weights.agents/governance/FAILURE-MODES.md. Historical motivations.agents/architecture/ADR-*.md. Decision records
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.
- yesterday First seen · 34 lines · 463 tokens per session scan A ccc01bc804b9
ai-agents governance.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 463 tokens to every session, about $0.0023 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 2026-09-03.
Other instructions, from other repositories
abtars AGENTS.md
AGENTS.md instructions for aksika/abtars, covering agents.md, quick commands, architecture, model-call chokepoint: spin(spec) (#1271) and external dependency: abmind.
Alex_Skill_Mall mall-maintenance-rules.instructions.md
Always-on routing for Mall maintenance work — fires the right Mall skill at the right moment. Distinguishes Mall-owned automation from out-of-scope editorial work.
gameforge AGENTS.md
Instructions for robcost/gameforge, covering general guidelines for working with nx, scaffolding & generators and when to use nxdocs.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.