← Back to .knowledge

// Blog / FAQ

FAQ: .knowledge for teams

A practical FAQ for teams that want coding agents to share repo-local context without pretending summaries are source of truth.

// direct answer

Short answer

.knowledge stores shared instructions and repository context beside the code. It helps agents start with the right files, shows when information may be outdated, and keeps code and tests authoritative.

Answer common team questions about adopting .knowledge and Pro2Pilot Inspector.

// team adoption

What teams are really asking

Teams do not only ask whether an agent can read a repo. They ask whether context survives handoff, whether stale summaries are visible, and whether reviewers can see what the agent trusted.

.knowledge answers those questions with files inside the repository instead of private chat memory.

Pro2Pilot Inspector adds a team dashboard for follow-up work, change impact, and policy checks.

// key principle

The rule to remember

Use .knowledge to route, inspect, and govern agent context.

Use current source and tests to decide behavior.

When trust is weak or freshness is stale, make the agent re-read code before making claims or changes.

// concrete example

A realistic adoption path

Start by adding .knowledge to one active repository and installing Codex, Claude Code, or OpenCode integrations.

First team trial checklist: install -> import -> release -> open Inspector -> generate PR summary -> review one agent PR.

Run import and release checks, then use the static Inspector to review trust and repair state.

Once the team sees repeated handoff or PR-review pain, add Inspector workflows on top of the free core.

// files you can inspect

Files that answer common questions

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.

Team entrypoint INCLUDED IN THE DOWNLOAD

.knowledge/Quick-Start.md

The first-read instructions live in the repo, not in one person's prompt notes.

Use it for
  • Team onboarding
  • Agent setup
Do not use it for
  • Behavior proof
Shared route CREATED DURING SETUP

.knowledge/maintenance/routing_bundle.json

Every agent can start from the same compact route.

Use it for
  • Session start
  • Module discovery
Do not use it for
  • Skipping source review
Shared trust state CREATED AFTER A HEALTH CHECK

.knowledge/maintenance/trust_report.json

The team can see what is trusted, stale, suspect, or low-confidence.

Use it for
  • Review readiness
  • Agent review rules
Do not use it for
  • Approving risky edits
Visual review CREATED AFTER A HEALTH CHECK

.knowledge/inspector/index.html

A generated Inspector makes trust and repair state easier to discuss.

Use it for
  • Team reviews
  • Repair planning
Do not use it for
  • Replacing current code

// commands to try

Commands and expected checks

node .knowledge/tools/install-agent-integrations.js
what it does
Team agent entrypoints are installed or refreshed.
where to look
.agents/skills/ .claude/skills/ and .opencode/commands/
node .knowledge/tools/flow.js import
what it does
Initial repository context is generated without overwriting curated knowledge.
where to look
.knowledge/project_index.json and .knowledge/modules/
node .knowledge/tools/flow.js release --no-color
what it does
Routing, confidence, freshness, metrics, search, and Inspector files are rebuilt.
where to look
.knowledge/maintenance/quality_report.json
FAQ grid files and checks

What teams need to decide

01 Does the repo own the context?
02 Can reviewers see trust and freshness?
03 Can multiple agents share the same first-read path?
04 Can source and tests override summaries?
05 Can outdated or unverified context become visible work?
06 Link map: Definition -> Onboarding -> Audit -> PR Impact -> FAQ

// practical reference

Team adoption questions

The practical answers should be inspectable in the repository.
QuestionShort answerFile to inspect
Is the core open source?Yes, the repo-local layer is open source and local-first..knowledge/tools/ and agent-integrations/
Does it replace tests?No. It routes agents toward the right tests.source files and test files
Does it replace RAG?No. It complements retrieval with trust and freshness.trust_report.json and search/index.json
Can teams review it?Yes, because the context is stored as repo files..knowledge/ and Inspector output
What is included in the download?Tools, docs, templates, integrations, starter files, Quick-Start, README, LICENSE, and NOTICE.public repo tree
What is created during setup?Routing, confidence, freshness, search, metrics, Inspector data, and PR summary.setup and health-check output
When is Inspector Pro useful?When the team wants visual repair, policy, and PR impact workflows./inspector/ and waitlist

// quick FAQ

FAQ

Is .knowledge a product or a standard?

The core is a repo-local open layer. Pro2Pilot builds product workflows, Inspector views, and team operations on top of it.

What should a team try first?

Install it in one active repository, run import and release, open the Inspector, and make one AI-generated PR include trust and source checks.

Why do some repository-specific files not appear in the public GitHub download?

Repository-specific files are created after setup or a health check; the public download includes the framework, templates, tools, docs, and starter files.

Which files are included and which are created later?

The download includes docs, tools, integrations, templates, Quick-Start, README, LICENSE, and NOTICE. Setup and health checks create routing, confidence, freshness, search, metrics, Inspector outputs, and PR summaries.

Does .knowledge use telemetry by default?

No. Update checks are disabled by default, there is no background updater, and no telemetry upload. Optional update checks query GitHub Releases and do not upload repo content.

// next step

Use this page when onboarding a team

Start with one repository, install integrations, run import and release checks, and show the team how trust state changes the agent workflow.