Context
The governance root is authored, not generated. It carries judgement that no tool produced and none should overwrite. Adoption usually stalls here, because the obvious integration is for the tool to own the file.
A repository whose rules were written by people
There is already a CLAUDE.md, an AGENTS.md or an equivalent that somebody wrote and others follow.
Fits when
- The authored text should stay authoritative and a generated section can sit inside it
- Enforcement already exists as git hooks, including dispatchers over a hook.d directory
- Rules are written down and nobody can currently prove which of them run
Does not fit when
- The repository wants a single generated instruction file and is happy to hand ownership over
- There is no governance to supervise yet, in which case start with the shipped skeleton instead
Both lists are required. An entry declaring only what it fits is refused by the generator and by majordomus doctor.
What you would do here
- Install the tool in one command, on a machine with no toolchainPaste one line, get a verified binary for this machine, and run majordomus init — no git, no Rust, no Node, no Python, no root, and no way to install an archive whose digest does not match.described version · init · doctor
- Adopt a repository that already has its own rulesInstall the supervisory layer into a repository with a hand-written CLAUDE.md, without the tool taking ownership of a file somebody else wrote.described init · update · doctor
- Prove a rule is actually enforced, not merely written downAnswer "is this rule real?" with a command rather than a reading of the source.described doctrine · doctor · check
- Find out what has drifted since anyone last lookedAsk what has moved, rather than whether anything is wrong.described watch · update · history
- Extend what the executable serves by adding a file, never by rebuilding itAdd a rule, a prompt or a knowledge node to .ai/ and have it appear as an MCP resource, an HTTP route and a reference entry, with the same binary.described init · update · doctor · knowledge
- Add a use case and let the tool prove itScaffold a draft for an uncovered command, validate it, run its scenario against the real tool, and see the coverage move.described usecase · doctor
- Move a repository from the pre-.ai layout to the layerSee what a migration would move, move it with a backup, and prove the result is a layer the tool reads.described migrate · doctor
- See which rules apply here and what enforces themList the effective rule set, read one rule as the tool reads it, and see which of them the tool enforces and from where.described rules · doctrine
- Decide what belongs in the AI context, as dataRead the repository’s declared scope policy, see which paths are in and out of the index, and let doctor and the knowledge index apply it rather than a hardcoded list.described knowledge · doctor
- Keep every provider bootstrap thin, generated and within budgetRegenerate AGENTS.md, CLAUDE.md and the other provider files from one policy and prove they are stamped, point at the layer, stay under the line budget and resolve every reference.described update · doctor · watch
- Trace a change to the context documents it affectsList the scoped context documents, resolve which apply to a path and why, and find out which documents a change set touches before it lands.described context · doctor
- Refuse a directory of the layer that documents nothingA directory added under the layer without a context document fails validation by name, nothing resolves against the tree until it says what it is for, and the same hierarchy is readable over MCP and the API without running the gate.described context · doctor
- Trust the policy and the profiles only after they are validatedProve that the canonical policy parses with every key it needs declared, that every profile parses and the default exists, and that what the policy declares as enforced is what actually runs.described doctor · check
- Follow a procedure the repository defines, and add another oneRead the repository''s skills, take one as it is written, and add a new one by writing its file — no registry, no code, and a check that says what it examined.described skills
- See what the repository holds, and run one of its capabilities, without reading a fileOpen the shared server in a browser and get the whole layer as pages: what exists, where each thing came from, what depends on what, what is failing, and a form that runs any capability.described doctor · knowledge
- Say what your work is for, once, and have every surface say itRecord an operational failure mode as one file and have the command line, the API, MCP and the website answer it without registering it anywhere.described init · context · knowledge · doctor