agentleFS
ImYourBoyRoyImYourBoyRoy/agent-continuity-stack/AGENTS.md

agent-continuity-stack

AGENTS.md1 starsChanged 4 months agoMITView on GitHub

This repository publishes repository-centered continuity through an optional portable user-global operating contract, memory conventions, client adapters, lifecycle safeguards, and on-demand Agent Skills for Codex, Cursor, Claude Code, and Google Antigravity. Keep skill content independent of an individual workstation, private project, account, or repository owner. - GLOBAL_CUSTOM_INSTRUCTIONS.md is the canonical complete Expert Agent Operating Contract. Do not summarize, trim, or independently edit client copies. - instruction-pack.json records its integrity and client adapters. - manifest.json owns package inventory and versions. - Each…

  • Reads credentials

The file

Show its rules and text

We split this AGENTS.md into the rules it gives an agent

13 rules. About 0 are common, 7 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the portable Agent Skills core: exact SKILL.md with only name and description frontmatter.

    line 38
  2. Distinctive:

    Keep activation descriptions discriminative and procedures in the body or directly linked references.

    line 40
  3. Distinctive:

    Do not add an executable remote installer.

    line 42
  4. Distinctive:

    Keep skill installation independent from custom-instruction installation.

    line 45
  5. Distinctive:

    Keep backups, receipts, baselines, and removed copies outside every client discovery root.

    line 48
  6. Very specific:

    Keep MEMORY.md local-only and Git-ignored.

    line 50
  7. Very specific:

    Keep Codex AGENTS.override.md and Claude CLAUDE.local.md plus .claude/settings.local.json local-only.

    line 57
  8. Very specific:

    Do not embed personal identity, home paths, emails, private hosts, credentials, device IDs, or private project schemas under skills/.

    line 62
  9. Distinctive:

    Keep optional skills uninstalled by default and require collision tests before adding one to the core tier.

    line 71
  10. Very specific:

    Update README.md, MEMORY.md, HANDOFF.md, ARCHITECTURE.md, CHANGELOG.md, manifests, activation cases, and client smoke tests when their …

    line 73
  11. Distinctive:

    Run from the repository root:

    line 81
  12. Very specific:

    Before release, run the client matrix in tests/CLIENT_SMOKE_MATRIX.md against the supported client versions.

    line 92
  13. Distinctive:

    Create a release archive only from an identified clean commit.

    line 96

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Agent Continuity Stack Instructions

Project purpose and boundary

This repository publishes repository-centered continuity through an optional portable user-global operating contract, memory conventions, client adapters, lifecycle safeguards, and on-demand Agent Skills for Codex, Cursor, Claude Code, and Google Antigravity. Keep skill content independent of an individual workstation, private project, account, or repository owner.

Authorities

  • GLOBAL_CUSTOM_INSTRUCTIONS.md is the canonical complete Expert Agent Operating Contract. Do not summarize, trim, or independently edit client copies.
  • instruction-pack.json records its integrity and client adapters.
  • manifest.json owns package inventory and versions.
  • Each skills/<name>/skill-manifest.json owns that skill's independent version.
  • optional_skills/ contains default-uninstalled capabilities declared separately in the package manifest.
  • schemas/ owns model-operated lifecycle record contracts.
  • integrations/ owns exact-tested specialist-toolkit boundaries.
  • INSTALL_PROTOCOL.md owns installation, update, backup, and rollback behavior.
  • CLIENT_COMPATIBILITY.md records version-sensitive discovery assumptions.
  • ARCHITECTURE.md records durable component, lifecycle, and trust boundaries.
  • MEMORY.md records verified durable project state.
  • HANDOFF.md records the concise current continuation point for another model.
  • CLAUDE.md is a one-line Claude Code import of the canonical AGENTS.md; do not duplicate project instructions there.

Repository policy and current host safety instructions retain their actual client-defined precedence.

Editing rules

  • Use the portable Agent Skills core: exact SKILL.md with only name and description frontmatter.
  • Keep activation descriptions discriminative and procedures in the body or directly linked references.
  • Do not add an executable remote installer. Installation remains model-driven, status-first, explicitly authorized, journaled one client at a time, and best-effort recoverable.
  • Keep skill installation independent from custom-instruction installation. Preserve existing instructions by default and require explicit review for guided additions or the complete contract.
  • Keep backups, receipts, baselines, and removed copies outside every client discovery root.
  • Keep MEMORY.md local-only and Git-ignored. Never stage, commit, release, or upload it unless the user explicitly authorizes sharing it.
  • For maintainer-authored commits and annotated tags, use the GitHub-linked account ImYourBoyRoy with @imyourboyroy as the Git name and an account-linked GitHub no-reply email. Do not use the public contact email as commit metadata, and preserve other contributors' and bot identities during any history rewrite.
  • Keep Codex AGENTS.override.md and Claude CLAUDE.local.md plus .claude/settings.local.json local-only; shared policy belongs in canonical AGENTS.md or tracked project settings.
  • Reject symlinks, junctions, reparse points, and unsupported special files in copied or restored trees.
  • Do not embed personal identity, home paths, emails, private hosts, credentials, device IDs, or private project schemas under skills/.
  • Maintain one workflow owner. Toolkit-managed Astro + Cloudflare implementation belongs to Portable Web Toolkit; generic skills may delegate but must not reproduce its commands or configuration systems.
  • For Python runtime-manager recommendations, follow the README's Python runtime preference only when neither the user nor repository already selects a manager. Never install it or replace the project's package manager or lockfile implicitly.
  • Keep optional skills uninstalled by default and require collision tests before adding one to the core tier.
  • Update README.md, MEMORY.md, HANDOFF.md, ARCHITECTURE.md, CHANGELOG.md, manifests, activation cases, and client smoke tests when their owned contract changes.
  • Increment a skill version for a material change to that skill. Increment the package version for a published package-level change.

Validation

Run from the repository root:

python3 scripts/validate_bundle.py
python3 scripts/inspect_contract.py source
python3 scripts/inspect_tree.py . --exclude .git --exclude .env \
  --exclude MEMORY.md --exclude AGENTS.override.md \
  --exclude CLAUDE.local.md --exclude .claude/settings.local.json
python3 tests/run_portable_tests.py

Before release, run the client matrix in tests/CLIENT_SMOKE_MATRIX.md against the supported client versions. A copied file is not evidence that a client loaded it.

Create a release archive only from an identified clean commit. Record the commit, release date, archive name, and SHA-256 in the release notes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.