← Back to .knowledge

// Blog / operational checklist

Codex repo onboarding checklist for .knowledge

The useful setup tool is not a longer prompt. It is a repeatable checklist Codex can verify inside the repository.

// direct answer

Short answer

A Codex onboarding checklist should confirm the .knowledge entrypoint exists, agent integrations are installed, routing and trust reports are current, and low-confidence modules are rechecked from source before edits.

Give Codex a repeatable repo-local onboarding path before asking it to change behavior.

// the problem

Repository setup is easy to lose between sessions

Codex can read and edit the local workspace, but a repo with no first-read path still forces the agent to infer structure from scattered files.

Instructions may live in chat, local notes, or an old README section. That makes onboarding hard to repeat across sessions.

The first useful fix is not a longer prompt. It is a small, repo-local checklist with commands and files the agent can verify.

// repeatable setup

Keep the onboarding checklist in the repository

Place .knowledge in the repository root, then make Quick-Start.md the first operational read.

Install the agent integrations so Codex, Claude Code, OpenCode, and other tools can find the same routing layer.

Run import once, then use release checks when meaningful work changes the repo or the knowledge state.

// concrete example

Before first behavior edit

Ask Codex to read .knowledge/Quick-Start.md, then read the Routing Bundle and the relevant module summary for the task.

Copy-paste prompt: Read .knowledge/Quick-Start.md, then verify routing_bundle.json, trust_report.json, and the target source/tests before editing.

If the module summary needs review, open the relevant source files and tests before planning the edit.

// files you can inspect

Files that guide Codex

Some repository-specific files appear only after setup or a health check. Run the documented setup workflow to create routing, confidence, freshness, search, metrics, and PR summary outputs.

First operational read INCLUDED IN THE DOWNLOAD

.knowledge/Quick-Start.md

This file tells the agent how to enter the knowledge layer without relying on chat memory.

Use it for
  • Starting a new Codex session
  • Finding maintenance commands
Do not use it for
  • Replacing task-specific source review
  • Assuming every summary is trusted
Routing check CREATED DURING SETUP

.knowledge/maintenance/routing_bundle.json

Codex needs this compact map before planning work across a large repository.

Use it for
  • Choosing modules
  • Finding stale or suspect context
Do not use it for
  • Making claims about runtime behavior
Trust check CREATED AFTER A HEALTH CHECK

.knowledge/maintenance/trust_report.json

The trust report shows whether knowledge is ready for routing or must be rechecked from source.

Use it for
  • Deciding how cautious to be
  • Finding low-confidence modules
Do not use it for
  • Approving code without tests
Codex integrations ADDED TO YOUR REPOSITORY

.agents/skills/*/SKILL.md

Installed skills give Codex reusable workflows instead of one-off instructions.

Use it for
  • Repeatable local workflows
  • Knowledge maintenance commands
Do not use it for
  • Hiding product-specific requirements from the repo
Codex repo contract ADDED TO YOUR REPOSITORY

AGENTS.md

The installer creates or updates AGENTS.md with .knowledge first-read rules for Codex.

Use it for
  • Repository starting instructions
  • Onboarding future Codex sessions
Do not use it for
  • Replacing current source and tests

// commands to try

Commands and expected checks

node .knowledge/tools/install-agent-integrations.js
what it does
Codex, Claude Code, OpenCode, and command entrypoints are installed or refreshed.
where to look
.agents/skills/ and .knowledge/agent-integrations/
node .knowledge/tools/flow.js import
what it does
The initial repository map and module summaries are created or refreshed.
where to look
.knowledge/project_index.json and .knowledge/modules/
node .knowledge/tools/flow.js release --no-color
what it does
Routing, trust, freshness, search, metrics, PR summary, and Inspector outputs are checked.
where to look
.knowledge/maintenance/quality_report.json
node .knowledge/tools/build-visual-inspector.js
what it does
The local static Inspector is regenerated.
where to look
.knowledge/inspector/index.html
Onboarding checklist files and checks

Before asking Codex to change behavior

01 Read .knowledge/Quick-Start.md
02 Install agent integrations
03 Run flow import
04 Confirm routing_bundle.json exists
05 Run release check
06 Open the local Inspector

// practical reference

Pass / fail setup checklist

A setup checklist should tell Codex what to do next when a check fails.
CheckPassFail / next move
Quick-Start existsUse it as the first operational read.Create or restore the .knowledge entrypoint.
Routing bundle existsUse it to choose source files.Run import or release before planning.
Trust report is currentPlan with its trust labels.Treat summaries as advisory and re-read source.
AGENTS.md existsCodex has repository-owned starting instructions.Run install-agent-integrations.
Agent integrations installedUse reusable Codex skills and commands.Run install-agent-integrations before handoff.

// quick FAQ

FAQ

Should Codex always run the full release flow before editing?

No. Use the release flow when setup, knowledge state, or meaningful repository changes need to be refreshed. For small tasks, reading the current routing and source files may be enough.

What if the trust report marks a module low-confidence?

Use the module summary only to find relevant files. Re-read current source and tests before making behavior claims or edits.

// next step

Before your first code change

Before a serious edit, confirm that Codex has read the repository entrypoint, Routing Bundle, confidence report, and the current source files for the task.