Reason, don't recite
A drift corrector for incumbency discipline. The method, re-anchor, audit
the work in flight, correct forward, report, and the tone that firing this
is not an accusation, lives in
${CLAUDE_PLUGIN_ROOT}/context/re-anchor-audit-correct.md.
Read it; this file adds only what is specific to interrogating inherited
content.
The discipline this re-anchors
Inherited content, a repo's docs, conventions, structure, processes, is
evidence of what is, never a self-justifying argument for what should
be. Resolve the source of truth per the method doc's ladder: if the
consuming project states an incumbency / first-principles rule in its own
CLAUDE.md / .claude/rules/, re-anchor THAT. Otherwise re-anchor this
portable baseline:
- Precedent describes, it does not justify. Existing structure,
coupling, "how it's always been done", and "I don't know why, it just is"
describe the current state; none is an argument that the state is correct.
- Descriptive-only support earns a challenge. A rule, boundary, or
process whose only backing is that it already exists gets re-derived from
first principles. State the actual purpose, then test whether the
incumbent form serves it, not obeyed on sight.
- A live rationale is different from inertia. A convention someone can
justify on its merits is followed; one coasting on incumbency is
interrogated. Separate the two before acting.
- Absence today is not out of scope. Do not dismiss a concern merely
because the thing it depends on does not exist yet; judge it on its
merits.
This is a distinct axis from /discipline:do-your-research. That skill
acquires external evidence you LACK; this one questions internal evidence
you INHERITED and took on faith. Firing it is a re-anchor, not an
accusation, a gentle "should we actually be doing it this way" is a
first-class use, and the audit may find every inherited choice is well
justified.
Audit. What to look for
Name concrete, located findings (per the method doc's step 2, self-audit):
- a decision justified only by precedent. "that's how this repo does it",
"the existing code does X, so match it", with no rationale stated;
- a convention followed while nobody can say what it is for;
- inherited structure treated as a hard constraint when it is only the
current state;
- a "we can't, it's always been this way" that was never re-derived;
- a concern waved off solely because its dependency does not exist yet.
Correct each forward now: re-derive the inherited choice from its actual
purpose, and either confirm it with a live rationale or challenge it with
the first-principles alternative. Do not stop at restating what the
inherited source says. Reason about whether it should still hold.
Reciprocal boundaries
Siblings carve their axes out of this one. Conformance to an EXTERNAL vendor's
current docs is
/discipline:recheck-against-upstream's axis; the production-side rule that
new work reuses or openly replaces an established way (never a silent second
way) is /discipline:reuse-or-replace's; a technology/dependency selection is
/discipline:pick-for-the-problem's. This skill owns the general evaluation
of inherited content's justification.
When the inherited content is a shared standard
Interrogating a shared convention can end in disagreement. Do not silently
deviate from it and do not silently conform to it. Route the disagreement
to /discipline:follow-our-standards, which owns taking a standards
disagreement upstream through the proper change path. It drafts the change
and routes it to the human, and does not open a standards PR (or any outward
artifact) without explicit opt-in. Degrade to that skill in prose when it is
not installed.
What this skill does NOT do
- Does not treat challenge as rejection. Re-derivation often confirms
the incumbent form; the duty is to reason, not to overturn.
- Does not fabricate a finding. Inherited content that stands on a live
rationale audits clean; say so rather than manufacturing dissent.
Gotchas
- The tell is a justification that only restates the incumbency. "because
that's what's there". A real rationale names a purpose the form serves;
inertia names only the form.
- Confirming an inherited choice is a valid outcome. This is not a mandate
to change things. It is a mandate to know WHY, and to re-derive when the
only answer is "it's always been like this".
1---2name: reason-dont-recite3description: Re-anchor the discipline that inherited content is evidence of what is, never self-justifying authority, then audit the work in flight for decisions coasting on precedent and re-derive them from first principles. Use when: 'reason don't recite', 'why is it this way', 'challenge that convention', 'you're deferring to precedent', "that's just how it's done", 'question the inherited design', 'stop reciting the docs', 'is this actually right', or at conversation start on legacy or inherited code. Note the shared phrasing: this skill challenges whether a convention should STILL hold and re-derives it from first principles; when the ask is instead to RECOVER the original reasoning from the historical record, review discussion, tickets, design documents, that is '/discovery:trace-intent' if the discovery plugin is installed, and otherwise read that record directly before challenging what it says.4---56# Reason, don't recite78A drift corrector for incumbency discipline. The method, re-anchor, audit9the work in flight, correct forward, report, and the tone that firing this10is not an accusation, lives in11[`${CLAUDE_PLUGIN_ROOT}/context/re-anchor-audit-correct.md`](../../context/re-anchor-audit-correct.md).12Read it; this file adds only what is specific to interrogating inherited13content.1415## The discipline this re-anchors1617Inherited content, a repo's docs, conventions, structure, processes, is18evidence of what *is*, never a self-justifying argument for what *should19be*. Resolve the source of truth per the method doc's ladder: if the20consuming project states an incumbency / first-principles rule in its own21`CLAUDE.md` / `.claude/rules/`, re-anchor THAT. Otherwise re-anchor this22portable baseline:2324- **Precedent describes, it does not justify.** Existing structure,25 coupling, "how it's always been done", and "I don't know why, it just is"26 describe the current state; none is an argument that the state is correct.27- **Descriptive-only support earns a challenge.** A rule, boundary, or28 process whose only backing is that it already exists gets re-derived from29 first principles. State the actual purpose, then test whether the30 incumbent form serves it, not obeyed on sight.31- **A live rationale is different from inertia.** A convention someone can32 justify on its merits is followed; one coasting on incumbency is33 interrogated. Separate the two before acting.34- **Absence today is not out of scope.** Do not dismiss a concern merely35 because the thing it depends on does not exist yet; judge it on its36 merits.3738This is a distinct axis from `/discipline:do-your-research`. That skill39acquires external evidence you LACK; this one questions internal evidence40you INHERITED and took on faith. Firing it is a re-anchor, not an41accusation, a gentle "should we actually be doing it this way" is a42first-class use, and the audit may find every inherited choice is well43justified.4445## Audit. What to look for4647Name concrete, located findings (per the method doc's step 2, self-audit):4849- a decision justified only by precedent. "that's how this repo does it",50 "the existing code does X, so match it", with no rationale stated;51- a convention followed while nobody can say what it is for;52- inherited structure treated as a hard constraint when it is only the53 current state;54- a "we can't, it's always been this way" that was never re-derived;55- a concern waved off solely because its dependency does not exist yet.5657Correct each forward now: re-derive the inherited choice from its actual58purpose, and either confirm it with a live rationale or challenge it with59the first-principles alternative. Do not stop at restating what the60inherited source says. Reason about whether it should still hold.6162## Reciprocal boundaries6364Siblings carve their axes out of this one. Conformance to an EXTERNAL vendor's65current docs is66`/discipline:recheck-against-upstream`'s axis; the production-side rule that67new work reuses or openly replaces an established way (never a silent second68way) is `/discipline:reuse-or-replace`'s; a technology/dependency selection is69`/discipline:pick-for-the-problem`'s. This skill owns the general evaluation70of inherited content's justification.7172## When the inherited content is a shared standard7374Interrogating a shared convention can end in disagreement. Do not silently75deviate from it and do not silently conform to it. Route the disagreement76to `/discipline:follow-our-standards`, which owns taking a standards77disagreement upstream through the proper change path. It drafts the change78and routes it to the human, and does not open a standards PR (or any outward79artifact) without explicit opt-in. Degrade to that skill in prose when it is80not installed.8182## What this skill does NOT do8384- **Does not treat challenge as rejection.** Re-derivation often confirms85 the incumbent form; the duty is to reason, not to overturn.86- **Does not fabricate a finding.** Inherited content that stands on a live87 rationale audits clean; say so rather than manufacturing dissent.8889## Gotchas9091- The tell is a justification that only restates the incumbency. "because92 that's what's there". A real rationale names a purpose the form serves;93 inertia names only the form.94- Confirming an inherited choice is a valid outcome. This is not a mandate95 to change things. It is a mandate to know WHY, and to re-derive when the96 only answer is "it's always been like this".
melodic-software