From ayanokoji
Reads PROGRESS.md and produces a strategic progress summary: completed tasks, retry rate, protocol adherence, and open blocker count. Measures whether the Ayanokoji verification gate is being honored. One-shot display. Use when the user says "show progress", "how are we doing", "ayanokoji-gain", or "/ayanokoji-gain".
How this skill is triggered — by the user, by Claude, or both
Slash command
/ayanokoji:ayanokoji-gainThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You have been invoked as `ayanokoji-gain`. Read PROGRESS.md (and TASK.md for
You have been invoked as ayanokoji-gain. Read PROGRESS.md (and TASK.md for
current task status) and produce a cold strategic summary. One shot — do NOT
modify any file.
Completed Tasks
List every completed task from the Completed Tasks table:
✓ <Task Name> — verified by: <verification method>
Retry Rate
Count tasks that appear in both Failed Attempts and Completed Tasks (they failed before succeeding). Report as:
Retry rate: <M>/<N> tasks required at least one retry.
A high retry rate means the approach phase is underspecified. Flag it if retry rate exceeds 30%.
Verification Quality
Were tasks marked complete with actual output (command result, test output, endpoint response), or with assertions ("it should work", "tests passed")?
Flag any completion entry that lacks concrete verification proof.
Protocol Adherence
Check:
Open Blockers
List every entry in Current Blockers.
PROGRESS SUMMARY
────────────────
Completed: <N> tasks
Retries: <M> tasks needed retry (<retry rate>%)
Open blockers: <count>
Completed Tasks:
✓ ...
✓ ...
Verification quality: STRONG / WEAK / MIXED
Protocol adherence: ADHERENT / DRIFT DETECTED
If PROGRESS.md has only the initial scaffold entry:
No tasks completed beyond scaffold initialization.
npx claudepluginhub atanu2k4/ayanokoji.md --plugin ayanokojiScans a codebase for architectural friction, presents candidates as a visual HTML report with before/after diagrams, and guides you through deepening refactors.