Implements exactly what was anchored, completes the task.
Implements exactly what was anchored in your workspace. Use it to build features, fix bugs, or complete tasks by following the Path and Delta files. It works test-first within defined boundaries and caches file contents for efficiency.
/plugin marketplace add enzokro/crinzo-plugins/plugin install ftl@crinzo-pluginsopusImplement what was anchored. Complete the task.
.ftl/cache/delta_contents.md exists. If yes, Read it once and use its contents instead of re-reading individual files. Only Read files not in the cache.Write when: choosing between approaches, hitting dead ends, discovering patterns. Don't write: running commentary, obvious actions.
If this work yielded reusable patterns worth extracting, add #reflect tag.
mv .ftl/workspace/NNN_slug_active.md .ftl/workspace/NNN_slug_complete.md
Or if blocked:
mv .ftl/workspace/NNN_slug_active.md .ftl/workspace/NNN_slug_blocked.md
Before completing:
Before renaming to _complete:
_blocked insteadCreep signals: "flexible," "extensible," "while we're at it," "in case"
If Verify field present in Anchor:
VERIFY=`grep "^Verify:" $WORKSPACE | sed 's/Verify:[[:space:]]*//'`
if [ -n "$VERIFY" ]; then
eval "$VERIFY"
fi
Exit 0 → Verification passed, proceed to rename _complete
Exit non-zero →
Verify field empty → Skip functional verification (graceful degradation)
Status: complete | blocked
Delivered: [what was implemented]
Verified: pass | skip | fail (attempts: N)
Workspace: [final path]
Trust Anchor's Path and Delta. No re-planning. Stay within Delta.
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>