ai-agents governance.instructions.md

ai-agents governance.instructions.md is an instructions file for GitHub Copilot from rjmurillo/ai-agents. It costs 463 tokens per session, scanned A, original, MIT.

Governance rules for files that define how other agents work, including human approval, architecture records, evidence, and agreement across roles.

In plain words
What is it for?
Reviewing or changing governance files, cross-role rules, and major policy decisions.
Why use it?
They prevent one contributor from silently changing system-wide agent policies without review or documented reasoning.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/rjmurillo/ai-agents/governance
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for ai-agents governance.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/governance.svg)](https://agentmods.dev/instructions/rjmurillo/ai-agents/governance)
Your own site
<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>
Per session 463 This file is loaded in full into every session.
When invoked 463 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash ccc01bc804b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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.

.github/instructions/governance.instructions.md · 34 lines

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

  1. Human approval. Changes MUST be reviewed and approved by a human maintainer. Auto-merge is prohibited for governance files.
  2. ADR required. Significant governance changes (new rules, policy reversals, removed constraints) MUST be accompanied by an Architecture Decision Record in .agents/architecture/.
  3. 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).
  4. Evidence required. Every added or changed normative line under .agents/governance/ MUST have one nearby evidence anchor in the same section: a Source: line, a Refs issue or PR, an ADR link, a retrospective link, or a Why: paragraph. Reviewers verify this with git diff -U3 -- .agents/governance/.
  5. No unilateral changes. A single specialist agent MUST NOT alter rules that govern other agents without consensus.

SHOULD

  1. Update canonical sources first. PROJECT-CONSTRAINTS.md is the index of record. New constraints SHOULD land there, with details in a dedicated governance file.
  2. Cross-link. SHOULD link new governance content from AGENTS.md and CLAUDE.md when it affects agent defaults.
  3. RFC 2119. Rules SHOULD use MUST / SHOULD / MAY to state requirement strength explicitly.

MUST NOT

  1. MUST NOT reduce security or review requirements without a unanimous-consensus ADR.
  2. 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
Changes

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.

  1. yesterday First seen · 34 lines · 463 tokens per session scan A ccc01bc804b9

Subscribe to this mod's changes

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.