alexion
52fc449824
Reworks the consume skill around two acceptance axes and two destinations, implementing the six issues filed from the first real consume run as one design. - Add trigger-ability as a second acceptance axis alongside generalizes, with its two premises; a pull-channel note now requires both (#9). - Give consume a push channel — the target's own CLAUDE.md — for knowledge that fails an axis but is still useful: specific residue or proactive rules (#10). - Name the general-lesson/specific-residue split and route each half (#12). - Make the step-5 plan report a complete ledger with a per-note trigger line, push write-set, ref-fixes, flagged-not-authored, and drops (#13). - Extend project cleanup to reconcile CLAUDE.md (capture-gated removal/trim) and fix references to deleted files wherever they land (#11). - Encode a branch-owned output location: project notes flat under 01 sources/claude/projects/, honoring any pre-existing grouping (#14). Records the resolved vocabulary in .claude/CONTEXT.md and the two-channel write decision in .claude/adr/0001. Closes #9 Closes #10 Closes #11 Closes #12 Closes #13 Closes #14
1.4 KiB
Consume writes the target's push channel, not only the vault
consume was scoped to write only inside the vault's 01 sources/claude/ area.
A real run showed that most mined knowledge is not wiki-shaped — specific residue and proactive rules belong in the target's own always-loaded CLAUDE.md — and dropping it lost real signal, while redoing the target-doc edits by hand after each run was toil.
We decided consume writes a second channel outside the vault, the target's CLAUDE.md, rather than only planning those edits for the user to apply.
Considered Options
- Plan-only — spell the target-doc edits out in the report and have the user apply them by hand. Rejected: the whole value is not redoing what the run already worked out.
- Auto-write both channels (chosen) — apply the target edits too, but present them as a distinct, independently-approvable write-set under the one plan-approval gate, so a write outside the vault is never a surprise.
Consequences
consume's blast radius now includes files outside the vault and outside the spec/task scaffolding it deletes.
The plan-approval gate is what keeps that safe: the target write-set is approved separately from the vault write-set, and a declined target write-set degrades to flagged suggestions.
Destructive edits to CLAUDE.md are gated on capture — an entry is removed or trimmed only when its general part is present in the wiki.