Skip to main content

Agent Governance Framework

This document is the canonical governance policy for agent-facing instructions in this repository. It remains a docs-guide/policies/ page, not a docs-guide/frameworks/ page, because canonical agent-file locations, overlap boundaries, and retirement targets are enforced governance decisions rather than optional improvement guidance. The approved governance model is:
  • one cross-agent baseline
  • one native adapter per supported agent family
  • one shared repo knowledge set
  • no policy drift between overlapping instruction files
Future governance changes must update the runtime files, validators, and this policy together.

Approved Canonical Layout

Approved target locations: Current implementation state:

Governance Taxonomy

Must-have canonical rules

These rules must live in the canonical cross-agent baseline and must not drift by agent:
  • destructive git safety
  • hook and validation policy
  • local preview port policy (3000 forbidden for agent-run Mintlify/preview sessions)
  • root allowlist policy
  • source-of-truth order
  • v1 freeze / legacy content boundary
  • branch and lock governance
  • path-migration discipline
These rules should be shared across agents unless a native adapter requires different syntax:
  • response and review hygiene
  • component and style conventions
  • route-placement heuristics
  • change-propagation expectations
  • generated-file handling
  • contributor workflow norms

Native adapter rules

Native adapter files should contain only:
  • tool-specific file format or metadata requirements
  • minimal bootstrap instructions for that tool
  • a pointer back to the canonical repo baseline
They should not become separate copies of the full repo policy.

Required Repo Knowledge for Every Agent

Every supported agent must be grounded in the same repo knowledge set:

Current Active Rule Inventory and Overlap Map

Retired Legacy Surfaces

These files were intentionally retired during the approved governance rollout and should not be recreated as active governance sources:

Overlap clusters

Resolved in Phase 9:
  • .github/AGENTS.md now carries disambiguating HTML comment; no longer a duplicate of root AGENTS.md
  • ASSISTANT.md is a redirect stub; canonical content at .mintlify/Assistant.md
  • .github/augment-instructions.md is archived; replaced by .augment/rules/
Remaining:
  • docs-guide/contributing/agent-instructions.mdx still contains contributor-facing parts of the policy set; reduce to a link to AGENTS.md in a future pass
  • ai-tools/agent-packs/* are generated from separate sources and must remain outputs, not canonical rule inputs

Approved Migration Map

The current governance contract maps legacy surfaces to the following destinations:

Prior Reports Incorporated

This policy incorporates the following prior reports and decisions:

Prior report: Root entry re-review (2026-03-16)

Relevant preserved findings:
  • not everything currently discussed in .allowlist is required at repo root
  • nested agent paths such as .github/copilot-instructions.md are not valid .allowlist entries because the root gate is root-only
  • the current repo still uses ASSISTANT.md, and legacy assistant surfaces were identified as move or retire candidates

Prior report: Agent root file decision set (2026-03-16)

Approved decision set carried forward into this policy:
Supporting notes preserved from the prior report, updated for Phase 9:
  • Codex should use AGENTS.md as the cross-repo baseline; .github/AGENTS.md adds Codex-specific task-isolation rules
  • GitHub Copilot should use .github/copilot-instructions.md
  • Claude Code should use .claude/CLAUDE.md
  • Cursor should use .cursor/rules/*.mdc
  • Windsurf should use .windsurf/rules/*.md
  • Augment Code should use .augment/rules/*.md
  • Mintlify chat widget reads .mintlify/Assistant.md — this is not an AI coding assistant adapter

Report Sources

Repo evidence

  • .github/AGENTS.md
  • .github/copilot-instructions.md
  • .github/augment-instructions.md
  • ASSISTANT.md
  • docs-guide/contributing/agent-instructions.mdx
  • ai-tools/agent-packs/README.md
  • ai-tools/agent-packs/claude/CLAUDE.md
  • ai-tools/agent-packs/cursor/rules.md
  • ai-tools/agent-packs/windsurf/rules.md
  • .codex/README.md
  • .codex/task-contract.yaml
  • operations/scripts/validators/governance/check-agent-docs-freshness.js
  • docs-guide/tooling/ai-tools.mdx
  • docs-guide/policies/root-allowlist-governance.mdx

Official external sources

Last modified on May 22, 2026