agentleFS
Sign inStart free
docxologydocxology/codomyrmex/docs/AGENTS.md

codomyrmex

AGENTS.md10 starsChanged 38 days agoMITView on GitHub

Version: v1.3.0 | Status: Active | Last Updated: March 2026 Agent coordination document for the docs/ directory. Guides AI agents navigating the documentation surface of the Codomyrmex ecosystem. The docs/ directory is organized into 21 thematic sections containing 1,218 Markdown files (reference/inventory.md): Volatile counts (modules, MCP tools, tests) live in reference/inventory.md; refresh with uv run python scripts/doc_inventory.py.

The file

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

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow development/documentation.md for curated markers, bootstrap scope, and validator expectations after substantive edits.

    line 31
  2. Distinctive:

    Prefer targeted hand edits over full-repo bootstrap.

    line 32
  3. Distinctive:

    Navigation consistency: Every document must have Navigation section with links to parent, siblings, and root

    line 80
  4. Very specific:

    Version stamping: All top-level docs must have version/status/date header

    line 81
  5. Distinctive:

    Real content only: No placeholder or auto-generated boilerplate — every file must contain substantive documentation

    line 82

≈ “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

Codomyrmex Agents — docs/

Version: v1.3.0 | Status: Active | Last Updated: March 2026

Purpose

Agent coordination document for the docs/ directory. Guides AI agents navigating the documentation surface of the Codomyrmex ecosystem.

Key Files

PathRole
reference/inventory.mdCanonical counts (modules, tests, MCP decorators, workflows)
development/documentation.mdAuthoring policy, Mermaid, bootstrap vs hand-edit
modules/AGENTS.mdModule doc ownership (enrich_module_docs vs src/)
agents/AGENTS.mdAgent documentation tree root
index.mdPublished docs entry

Dependencies

  • Source of truth: src/codomyrmex/ and root SPEC.md / AGENTS.md; this tree explains and links, it does not replace code.
  • Authoritative numbers: volatile counts (tests, MCP tools, gate weights) live in docs/manuscript/config.yaml and docs/reference/inventory.md — never hard-code them in prose.
    • Gate weights: docs/manuscript/config.yaml → experiment.gate_score_weights (budget: 0.30 / risk: 0.30 / trust: 0.25 / completeness: 0.15)
    • Colony kernel subsystems: 8 — PheromoneStore, ResourceLedger, ActuationGate, ConsequenceMemory, RoleAdapter, PruningDaemon, FalsificationWorker, ColonyKernel (coordinator); sources: standalone modules under src/codomyrmex/colony_kernel/ plus kernel.py
    • MCP tools: 8 exposed by the colony control plane; source: src/codomyrmex/colony_kernel/mcp_tools.py
    • Attack vectors: CIRCULAR_ARCHITECTURE (not CIRCULAR_DEPS) — see src/codomyrmex/colony_kernel/falsification/worker.py
  • Tooling: uv for scripts (scripts/doc_inventory.py, scripts/documentation/validate_agents_structure.py); optional site build per pyproject.toml / Docusaurus under src/codomyrmex/documentation/ when publishing.

Development Guidelines

  • Follow development/documentation.md for curated markers, bootstrap scope, and validator expectations after substantive edits.
  • Prefer targeted hand edits over full-repo bootstrap; keep Operating Contracts below for navigation and mirror rules.
  • Refresh volatile numbers via uv run python scripts/doc_inventory.py --pytest before updating reference/inventory.md or root README.md.

Documentation Architecture

The docs/ directory is organized into 21 thematic sections containing 1,218 Markdown files (reference/inventory.md):

Core references (top level)

FilePurpose
ARCHITECTURE.mdSystem architecture, layers, module graph
DEPENDENCIES.mdDependency compatibility guide
PAI.mdPersonal AI Infrastructure hub
PAI_DASHBOARD.mdDashboard functionality matrix
SPEC.mdDocumentation-area functional specification (root SPEC.md is authoritative for the whole repo)
index.mdDocumentation site entry point

Volatile counts (modules, MCP tools, tests) live in reference/inventory.md; refresh with uv run python scripts/doc_inventory.py.

Thematic Sections

SectionFocusKey Content
agents/AI agent integrations40 packages plus the open_gauss submodule mirror src/codomyrmex/agents/ (+ agents/rules/ docs-only); Hermes: agents/hermes/AGENTS.md, skills.md
agi/AGI theoryEssays on emergence, category theory, agency
bio/Biological simulationBioSimulator, genetic algorithms
cognitive/Cognitive systemsCerebrum, Bayesian networks, active inference
compliance/RegulatoryAudit frameworks, data governance
deployment/DevOpsCI/CD, containers, cloud deployment
development/Developer guidesEnvironment setup, testing, coding standards
examples/TutorialsExecutable demos and integration examples
getting-started/OnboardingQuickstart, installation, learning path
integration/Cross-moduleIntegration patterns, MCP bridges
manuscript/ManuscriptColony Kernel paper source, tokens, and rendering pipeline
modules/Module docs132 top-level packages; ownership hub modules/AGENTS.md (see reference/inventory.md)
pai/PAI systemDashboard, skills, memory, dispatch
plans/RoadmapRelease plans, version targets
project/StandardsContributing, architecture, coding style
project_orchestration/WorkflowsMulti-agent coordination, orchestration
reference/API docsCLI tools, configuration reference
security/SecurityThreat models, audit, secret management
skills/Agent skillsSkill creation, registry, testing
todo/BacklogPer-module scope documents (todo/README.md)

Operating Contracts

  1. Docs mirror src/: The docs/agents/ structure mirrors src/codomyrmex/agents/ with a documentation subfolder for each agent framework
  2. Navigation consistency: Every document must have Navigation section with links to parent, siblings, and root
  3. Version stamping: All top-level docs must have version/status/date header
  4. Real content only: No placeholder or auto-generated boilerplate — every file must contain substantive documentation

Key Patterns

  • Signposting: Parent/child/sibling links in every document
  • Cross-references: Source docs link to doc docs and vice versa via relative paths
  • Hierarchical AGENTS.md: Root → docs/AGENTS.md → docs/agents/AGENTS.md → per-agent AGENTS.md
  • Mermaid: development/documentation.md — theme-neutral diagrams, subgraph conventions, normalizer scripts under scripts/

Navigation

  • Parent: AGENTS.md — Root agent coordination
  • Project Root: README.md — Project overview
  • Source: src/codomyrmex/ — Source code

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.

Check your setup, free