A fresh agent answering "what is a commander, how do I start one" has nothing to answer from, and invents. The mechanism to fix that already existed and had one user: skills/load.ts compiles an INDEX into every session — name, when to reach for it, path — and the body costs nothing until the agent opens it. The exact inverse of an affordance, which sends its body always and its description never. So no affordance was added, and that is the correction worth recording: an affordance saying "there is a platform skill" would be a second copy of the index entry, paid for on every turn to say what is already there. Affordances are facts about the CLIENT; this is reference material. The platform skill is GENERATED, because a hand-written one rots and we measured it — Spotlight's settings list drifted in two days, CLAUDE.md claimed 27 permissions against 18 and twenty PM2 entries against thirteen. A wrong skill is worse than a wrong doc: an agent quotes it with confidence and the user cannot tell. Generated: every permission with its kind, label, description, API prefixes, sockets, screens, self-service routes and read-only-writes; and the keyboard shortcuts. Prose, kept beside the generator so the two cannot separate: what the platform is, what each KIND means for a user, and where to look next. It also says what it does NOT cover — installed plugins vary per machine so a generated list would be wrong on every other server, and request shapes are not in the registry — plus a closing instruction not to guess, on the grounds that a question the registry cannot answer is one this file cannot either. docs:check regenerates it into memory and fails if the committed file differs. Verified both directions: appending one line made it fail naming the file, and regenerating made it pass. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
170 lines
6.3 KiB
TypeScript
170 lines
6.3 KiB
TypeScript
/*
|
|
Does the documentation still match the code?
|
|
|
|
── Why a script and not a habit ──
|
|
|
|
"Update the docs before a deploy" is a step that gets skipped at two in the morning, and its absence is
|
|
invisible. Every piece of drift found on 2026-08-22 was MECHANICAL — a count, a route name, a process
|
|
list — so it is checkable, and a check that exits non-zero cannot be quietly not done.
|
|
|
|
What it will not do is read prose and judge it. It looks only at claims with a machine-checkable
|
|
counterpart, which is a small fraction of the documentation and the fraction that rots fastest, because a
|
|
number is exactly the thing nobody re-derives while editing a sentence around it.
|
|
|
|
Real examples this was written from, both live at the time:
|
|
|
|
platform/CLAUDE.md "27 entries as of 2026-08-13" → the registry held 18
|
|
officer-dev/CLAUDE.md "Officer is twenty PM2 entries" → there were 13
|
|
Spotlight's settings list 9 rows against 21 sections, and one route that does not exist
|
|
|
|
── The rule for adding a check ──
|
|
|
|
A check must compare a documented claim against a value DERIVED AT RUN TIME, never against a second
|
|
hard-coded copy. A check with the answer written into it is one more place to drift, and it will drift in
|
|
the same edit that misses the doc.
|
|
*/
|
|
|
|
import { readFileSync, existsSync } from 'node:fs';
|
|
import { join, resolve } from 'node:path';
|
|
|
|
type Finding = { file: string; claim: string; documented: string; actual: string };
|
|
type CheckResult = { findings: Finding[]; skipped?: string };
|
|
|
|
const ROOT = resolve(import.meta.dir, '..');
|
|
const WORKSPACE = resolve(ROOT, '..');
|
|
|
|
const read = (path: string): string | null => (existsSync(path) ? readFileSync(path, 'utf-8') : null);
|
|
|
|
/** Spelled-out numbers appear in prose more often than digits, and both need catching. */
|
|
const WORDS: Record<string, number> = {
|
|
ten: 10,
|
|
eleven: 11,
|
|
twelve: 12,
|
|
thirteen: 13,
|
|
fourteen: 14,
|
|
fifteen: 15,
|
|
sixteen: 16,
|
|
seventeen: 17,
|
|
eighteen: 18,
|
|
nineteen: 19,
|
|
twenty: 20,
|
|
'twenty-one': 21,
|
|
'twenty-two': 22,
|
|
'twenty-three': 23,
|
|
'twenty-four': 24,
|
|
'twenty-five': 25,
|
|
};
|
|
const asNumber = (raw: string): number | null => {
|
|
const digits = Number(raw);
|
|
if (Number.isFinite(digits)) return digits;
|
|
return WORDS[raw.toLowerCase()] ?? null;
|
|
};
|
|
|
|
/**
|
|
* A documented count, found by a pattern with one capture group, compared to the live value.
|
|
*
|
|
* Returns a finding per MISMATCH, not per occurrence: a doc stating the right number twice is fine.
|
|
*/
|
|
function checkCount(file: string, pattern: RegExp, actual: number, claim: string): CheckResult {
|
|
const body = read(file);
|
|
if (!body) return { findings: [], skipped: `${file} not found` };
|
|
const findings: Finding[] = [];
|
|
for (const match of body.matchAll(pattern)) {
|
|
const stated = asNumber(match[1] ?? '');
|
|
if (stated === null || stated === actual) continue;
|
|
findings.push({ file, claim, documented: String(stated), actual: String(actual) });
|
|
}
|
|
return { findings };
|
|
}
|
|
|
|
async function main(): Promise<void> {
|
|
const all: Finding[] = [];
|
|
const skipped: string[] = [];
|
|
const record = (r: CheckResult) => {
|
|
all.push(...r.findings);
|
|
if (r.skipped) skipped.push(r.skipped);
|
|
};
|
|
|
|
// 1. How many permissions the registry holds. The number appears in prose and is never recomputed.
|
|
const { PERMISSIONS } = await import('../src/servers/permissions/registry');
|
|
record(
|
|
checkCount(
|
|
join(ROOT, 'CLAUDE.md'),
|
|
/([0-9]+|[a-z-]+) entries as of/gi,
|
|
PERMISSIONS.length,
|
|
'permission registry entries',
|
|
),
|
|
);
|
|
|
|
// 2. How many PM2 entries Officer is. Documented as going stale "every time a sidecar lands", which is an
|
|
// admission that it needs a check rather than a caveat.
|
|
const pm2 = Bun.spawnSync([process.env.SHELL || '/bin/sh', '-ic', 'pm2 jlist'], { stdout: 'pipe', stderr: 'pipe' });
|
|
if (pm2.exitCode === 0) {
|
|
try {
|
|
const list = JSON.parse(pm2.stdout.toString()) as Array<{ name: string }>;
|
|
const officer = list.filter((p) => p.name === 'officer' || p.name.startsWith('officer-')).length;
|
|
record(
|
|
checkCount(
|
|
join(WORKSPACE, 'CLAUDE.md'),
|
|
/Officer is ([a-z-]+|[0-9]+) PM2 entries/gi,
|
|
officer,
|
|
'officer PM2 entries',
|
|
),
|
|
);
|
|
} catch {
|
|
skipped.push('pm2 jlist did not parse');
|
|
}
|
|
} else {
|
|
// Honest rather than silent: a machine with no pm2 cannot check this, and saying so is the point.
|
|
skipped.push('pm2 unavailable — PM2 entry count unchecked');
|
|
}
|
|
|
|
// 3. Every settings path Spotlight offers must exist as a declared section. This is the drift that shipped
|
|
// a dead link to /settings/users, and it is the class the other two cannot catch: a name, not a count.
|
|
const { SPOTLIGHT_SETTINGS_PATHS } = await import('./docs-check-settings');
|
|
const declared = await SPOTLIGHT_SETTINGS_PATHS();
|
|
for (const bad of declared.missing) {
|
|
all.push({
|
|
file: 'Spotlight/useSpotlightItems.ts',
|
|
claim: 'settings route offered by Spotlight',
|
|
documented: bad,
|
|
actual: 'no screen declares that section',
|
|
});
|
|
}
|
|
|
|
// 4. The generated platform skill must match its generator. A stale SKILL.md is worse than a stale doc:
|
|
// an agent quotes it to a user with no way to tell it is out of date.
|
|
const { renderPlatformSkill, SKILL_PATH } = await import('./gen-platform-skill');
|
|
const expected = await renderPlatformSkill();
|
|
const onDisk = read(SKILL_PATH);
|
|
if (onDisk === null) {
|
|
all.push({
|
|
file: 'capabilities/skills/platform/SKILL.md',
|
|
claim: 'generated platform skill',
|
|
documented: 'missing',
|
|
actual: 'run `bun run skills:platform`',
|
|
});
|
|
} else if (onDisk !== expected) {
|
|
all.push({
|
|
file: 'capabilities/skills/platform/SKILL.md',
|
|
claim: 'generated platform skill is stale',
|
|
documented: `${onDisk.split('\n').length} lines on disk`,
|
|
actual: `${expected.split('\n').length} lines from the generator — run \`bun run skills:platform\``,
|
|
});
|
|
}
|
|
|
|
for (const note of skipped) console.log(` skipped: ${note}`);
|
|
if (all.length === 0) {
|
|
console.log('docs:check — every checkable claim matches the code');
|
|
return;
|
|
}
|
|
console.log(`\ndocs:check — ${all.length} claim(s) no longer match the code:\n`);
|
|
for (const f of all) {
|
|
console.log(` ${f.file}`);
|
|
console.log(` ${f.claim}: says ${f.documented}, actually ${f.actual}\n`);
|
|
}
|
|
process.exit(1);
|
|
}
|
|
|
|
await main();
|