Akinator PM — Development agent for Claude Code
Use at plan and verify stations to check batch discipline and completion honesty.
How to install Akinator PM
Installs to ~/.claude/agents/ihabkhaled-akinator-ai-akinator-pm.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ihabkhaled/akinator-ai/HEAD/agents/akinator-pm.md -o ~/.claude/agents/ihabkhaled-akinator-ai-akinator-pm.md Restart Claude Code, or start a new session, for it to be picked up.
What Akinator PM does
name: akinator-pm description: Use at plan and verify stations to check batch discipline and completion honesty. Reviews whether batches are cut on real seams, whether scope has crept, and whether every done claim has evidence behind it. Vetoes done claims without evidence. tools: Read, Grep, Glob, Bash
The Project Manager
You review as the person who has to report status to someone who will act on it. A false "done" is worse than a known "not started", because it gets built upon.
Y
Alternatives in Development
- Senior Engineer P7 — P7 Senior Engineer Agent 19.5k ★
- PR Commenter Batch — Posts sanitized batches of PR review comments or replies through configured review tooling 548 ★
- PR Check Watcher — Watches a GitHub PR's CI checks to completion via gh pr checks --watch and reports a concise pass/fail summary 289 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Akinator Librarian
Use at the end of every batch, before it is called done, to verify the knowledge delta. Reviews taxonomy routi
Akinator Product Owner
Use at plan and verify stations when work adds, changes or removes user-facing behavior. Reviews whether the f
Copilot Verifier
Independent verification of /copilot run quality. Audits fix accuracy, scope discipline, tracking honesty, and
Cutter
Turn recorded biographies into the shaped scene-list of a novel — the documentary editor's cut. Given the exha
Tech Claim Examiner
A third-party CTO-perspective examiner that evaluates resume technical claims using the 5-axis framework (A1 T
Edit Critic
Adversarially review a finished cut against its own source material before delivery — every on-screen claim tr
Related Skills
Claudemd Sampling Audit
Retrospective batch scan of historical transcripts for 8 self-enforced HARD rules — text detectors (§10-V bann
Completion Audit
Skill: Completion audit — mandatory before any "done" claim
Did You Check
Checks whether the Claude Code best practices were actually followed, and blocks the turn when they were not:
