// Maintain the project wiki in vault/. Use at the end of any session that produced a decision, fact, or state change. Extracts entities, updates topic pages, adds cross-links, never deletes. Pairs with the post_cascade_response_with_transcript hook.
Use ast-grep for structural (AST-aware) code search and refactoring instead of plain ripgrep when the intent depends on code structure — not just text matching. Triggers on refactors, codemods, "find all X that don't Y", or any search where naive grep would miss edge cases.
Guides proactive /compact usage with preservation instructions to prevent context rot in long Cascade sessions. Triggers when context reaches ~50% of window, before large tool outputs, or when the user mentions "context", "compact", "drift", or "forgetting".
Use when any non-trivial task (>20 LOC or >1 file) would otherwise be done without a persistent plan. Produces and maintains a markdown plan file that survives session compaction and restarts. Based on the Manus-style planning pattern popularized by OthmanAdi/planning-with-files (18.4k⭐).
Turn a feature branch into a clean, reviewable PR. Squash WIP commits, polish messages, verify green checks, draft PR description. Invoke right before opening a PR.
Scan a diff, branch, or working tree for leaked secrets, API keys, tokens, private keys, and PII before commit. Blocks the operation on CRITICAL findings, warns on MEDIUM. Pairs with the pre_commit hook.
Fill test coverage gaps to hit the project's target (AGENTS.md says ≥80% on src/). Reads existing tests to match style, prioritizes public-API and error paths, runs the suite after every batch.
| name | wiki-update |
| description | Maintain the project wiki in vault/. Use at the end of any session that produced a decision, fact, or state change. Extracts entities, updates topic pages, adds cross-links, never deletes. Pairs with the post_cascade_response_with_transcript hook. |
After a session, update the project's vault/ so future sessions have the context.
The session did at least one of:
vault/decisions/ADR-NNN.mdvault/people/<name>.md + link from vault/services/<svc>.mdvault/incidents/YYYY-MM-DD-<short>.md with root cause + fix + invariant to add to AGENTS.mdvault/glossary.mdIf none of those happened, output "no wiki updates needed" and stop.
vault/INDEX.md to know the current shape of the wiki.[[wikilinks]] between entities. If you reference a page that doesn't exist, create a stub with a "TODO" note.> **Stale as of YYYY-MM-DD:** ... and add the new section below.vault/INDEX.md with any new pages.vault/decisions/ before picking a number.# ADR-NNN: <Decision title>
**Status:** Proposed | Accepted | Deprecated | Superseded by ADR-XXX
**Date:** YYYY-MM-DD
**Author:** <name or @role>
## Context
Why are we deciding this now? What forces are at play?
## Decision
What are we doing?
## Consequences
### Positive
-
### Negative
-
### Neutral / Follow-up
-
## Alternatives Considered
- **<Alternative 1>** — rejected because...
- **<Alternative 2>** — rejected because...
# YYYY-MM-DD: <One-line title>
**Severity:** SEV1 | SEV2 | SEV3
**Duration:** X hours
**Customer impact:** <facts, numbers>
## Timeline
- HH:MM — first symptom observed
- HH:MM — on-call paged
- HH:MM — mitigation started
- HH:MM — resolved
## Root cause
One paragraph. Factual, not blame-assigning.
## Contributing factors
- Factor 1
- Factor 2
## What went well
-
## What could have gone better
-
## Action items
- [ ] **<Owner>** — <action> — by <date>
## Invariant to add to AGENTS.md
(If this incident reveals a rule that should be constitutional, write it here and add to AGENTS.md.)