agentic-os
AGENTS.md2 starsChanged 5 months agoMITView on GitHub
You are operating inside the agentic-os template: a sanitized harness for building a personal operating system with agents, memory, rules, hooks, scripts, and skills. Claude Code remains the canonical runtime for deterministic hooks. Codex can operate this repo as an execution surface when it reads this file and the control-plane contract below. When a task depends on Claude Code hooks firing, say so explicitly. Codex can read and edit the harness, but it does not automatically execute .claude/settings.json hooks unless…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository24 other files it gives its agents.
- control-plane/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- control-plane/CLAUDE.mdCLAUDE.md
- agentic-os-reference-syncSkill
- branch-cleanupSkill
- capture-triageSkill
- darwin-housekeepingSkill
- darwin-path-modeSkill
- decision-log-entrySkill
- eodSkill
- expert-interview-guideSkill
- feedback-intakeSkill
- harness-onboardingSkill
- ingest-contentSkill
- meeting-to-work-itemsSkill
- memory-consolidateSkill
- morning-briefSkill
- os-bootstrap-extendSkill
- os-bootstrapSkill
- pr-reviewSkill
- scheduleSkill
- spec-cross-checkSkill
- ux-critiqueSkill
- weekly-retroSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Check for .bootstrap-pending at repo root.
- Very specific: line 39
When a task depends on Claude Code hooks firing, say so explicitly.
≈ “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.
Files
agentic-os - Root Orientation for Codex
You are operating inside the agentic-os template: a sanitized harness for building a personal operating system with agents, memory, rules, hooks, scripts, and skills.
Claude Code remains the canonical runtime for deterministic hooks. Codex can operate this repo as an execution surface when it reads this file and the control-plane contract below.
On Session Start
- Check for
.bootstrap-pendingat repo root. If present, the template has not been configured. Invoke theos-bootstrapskill before other work. - Read
control-plane/session-start.md. - Read
control-plane/AGENTS.md. - Confirm with one line and wait for input. Do not summarize what you read.
Key Paths
control-plane/memory/self/- principal identity, preferences, boundariescontrol-plane/memory/<interface-agent>/- interface-agent mandate and execution standardscontrol-plane/memory/<senior-advisor>/- senior-advisor mandate and escalation rulescontrol-plane/memory/auto/MEMORY.md- persistent memory indexcontrol-plane/memory/decisions/decision-log.md- strategic decision register.claude/agents/- canonical agent specs.claude/skills/- canonical skill definitionscontrol-plane/registry/- agent and domain indexescontrol-plane/rules/- operating rulescontrol-plane/best-practices/- portable operating practicescontrol-plane/config/- spoke owners, protected repos, trigger rules.claude/settings.jsonand.claude/hooks/- Claude Code hook wiring
Critical Conventions
- The interface agent is the single voice to the principal.
- The senior advisor pressure-tests internally and never speaks to the principal directly.
- Entity guardians protect declared non-negotiables before time-consuming proposals reach the principal.
- Output to the principal: direct answer -> recommendation -> so what -> brief rationale -> open questions only if needed.
- Preserve unrelated working-tree changes. Do not reset, remove, or overwrite parallel work unless explicitly asked.
Runtime Note
When a task depends on Claude Code hooks firing, say so explicitly. Codex can read and edit the harness, but it does not automatically execute .claude/settings.json hooks unless the local Codex environment has equivalent wiring.
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
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.