the-room-of-requirement
Skill9 starsChanged 3 months agoMITView on GitHub
Author a first memory file for a repo that has none — derived from the repo's actual build/test commands, its real conventions, and its correction history, never invented. The one generative pass in this book: it proposes a file, you approve it, exactly like any other fix-table row. Use for "this repo has no CLAUDE.md", "write me a starter memory file", "set up Claude for this project", "what should my AGENTS.md say", or when a triage finds no instruction layer to audit. Deliberately small — tens of lines, not hundreds. NOT for improving a memory file that already exists (→ clarificus-maxima, obliviate-fossilium, and the rest of the book). NOT for authoring skills, agents, or hooks.
In this repository20 other files it gives its agents.
- accio-rulebookSkill
- alohomoraSkill
- avada-verbosaSkill
- clarificus-maximaSkill
- configureSkill
- contradicto-revelioSkill
- descriptio-reducioSkill
- finite-recursumSkill
- legilimens-anthropicaSkill
- muffliato-hookusSkill
- nihil-revelioSkill
- obliviate-fossiliumSkill
- opus-pocusSkill
- priori-incantatoSkill
- protegoSkill
- quietus-capslockiusSkill
- sorting-hatSkill
- tempus-mutaturSkill
- the-pensieveSkill
- the-remembrallSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Every other pass in this book grades instructions that exist.
- Distinctive: line 33
Derive, never invent: Every proposed line cites what it came from — a script name, a workflow step, a config key, a transcript correction.
- Distinctive: line 44
The two or three conventions a new contributor gets wrong: Not the style guide — the surprises.
- Distinctive: line 59
What a linter already enforces: If the formatter fixes it, prose about it is unread text that competes with rules that matter.
- Distinctive: line 81
Follow whatever the repo already leans toward: CLAUDE.md for a Claude-only project, AGENTS.md when the repo is multi-tool or already …
- Distinctive: line 91
Read-only until approved, like every other pass: propose, then write only what the user accepts.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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
🦋 The Room of Requirement
"Your repo asked for instructions it never had. Here they are."
Every other pass in this book grades instructions that exist. A repo with no memory file gets nothing from them — a full sheet of honest verdicts of no subject, truthful and useless. That repo is the one most likely to benefit from anything at all, and it is the one the book had no answer for.
This is the only pass that writes rather than grades. It still proposes: the file is a fix-table row like any other, and nothing lands until the user approves it.
What to scan
Inputs, in order of authority. Later sources never override earlier ones — they fill gaps.
- The repo's own machinery. Package manifests and lockfiles (which package manager is real,
not which is fashionable), script targets, CI workflow steps, linter and formatter config,
test runner config, the directory layout, and whatever
.gitignoreand generated-file markers say is not hand-written. - README and CONTRIBUTING. Conventions the project already states in prose. Extract, do not restate: if the README says it well and the model reads the README, the memory file needs the rule only when a session would act wrongly without it.
- Correction history, if it exists.
the-remembrall's clusters are the strongest possible input here — a rule the human has already had to give three times, with its wording settled. Skip this input silently when there are no transcripts; do not block on it.
Derive, never invent. Every proposed line cites what it came from — a script name, a workflow step, a config key, a transcript correction. A line you cannot cite is a guess about someone else's project, and it will be obeyed exactly as hard as the true ones.
What goes in
Four things, and the file is mostly done:
- The commands. Build, test, lint, typecheck, run — exact and copy-pasteable, with the right package manager. This is the single highest-value content and the one thing the model cannot infer reliably: it self-verifies its reasoning, not your toolchain.
- The two or three conventions a new contributor gets wrong. Not the style guide — the surprises. Which directory is generated, which file is the source of truth for a value that appears in three places, the import path that looks right and isn't.
- What is generated or vendored. Anything hand-edits get overwritten in, anything a tool owns. Cheap to state, expensive to discover by losing work.
- Anything destructive that must be confirmed first. Migrations, deploys, history rewrites, anything that reaches a shared system.
What never goes in
These are the anti-patterns — authored fresh, they arrive pre-broken, and the rest of the book would flag them on its next pass:
- Aspirational values. "We value simplicity", "write clean code" — no trigger, no scope,
not falsifiable.
clarificus-maximaclass 3 and 4, shipped on day one. - What a linter already enforces. If the formatter fixes it, prose about it is unread text that competes with rules that matter. Mechanism beats prose; the mechanism is already there.
- Restatements of the README. Duplication drifts, and the drifted copy wins in novel situations because it matches more contexts.
- Anything the model infers from the code. Language, framework, obvious layout. Text confirming what is already visible costs attention and buys nothing.
- Emphasis. No
CRITICAL, noYOU MUST, no caps. A file authored today has no scar tissue to justify shouting, and the 5-family over-obeys it —quietus-capslockiuson a file this book wrote would be an embarrassment. - Verification prose. "Double-check your work" is redundant on this model family. A rule naming a concrete command is not verification prose and belongs in — that is the commands section above.
Size
Target tens of lines. Treat a hundred as a signal you are inventing. Most of this book's effort goes into shrinking files that grew for years; authoring a large one would be a strange way to start. If the repo genuinely needs more than that, the excess is usually per-directory content — propose a nested file where it applies, not more root.
Which file
Follow whatever the repo already leans toward: CLAUDE.md for a Claude-only project, AGENTS.md
when the repo is multi-tool or already carries other agent config. If neither exists and there is
no signal, offer both names and let the user pick — the content is identical either way.
Bounds
- Scope: authoring one memory file for this repo. Not skills, not agents, not hooks, not CI. Not a second file unless the first proved genuinely too small.
- Cap: one proposal, tens of lines. If a section is running long, that content probably belongs in a nested file or does not belong at all.
- Done when a proposal exists and every line in it cites its source. Not when the file feels complete — a starter file is meant to be added to by the people who hit the gaps.
- This pass is
N/Awhen a memory file already exists. Its triage row is the inverse of every other pass in the book: it runs only on a repo the rest have nothing to say about. Improving an existing file is the rest of the book's job. - Read-only until approved, like every other pass: propose, then write only what the user accepts.
- See
skills/opus-pocus/references/casting-safety.mdfor the full rules.
Report format
The proposed file in full, then a source table: every line or section against the input it was
derived from (package.json:scripts.test, .github/workflows/ci.yml:19, a transcript correction
with its date). Then what you deliberately left out and why — the reader needs to see the
restraint to trust the inclusions.
SCANNED NOTHING if the repo has no manifests, no CI, no README, and no transcripts — there is
nothing to derive from, and inventing a file from an empty repo is exactly the guess this pass
refuses to make.
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.

