Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/skywalkercyt/mp-implement/verification-before-completionnpx skills add skywalkercyt/mp-implement --skill verification-before-completiongit clone --depth 1 https://github.com/skywalkercyt/mp-implementWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00042 | $0.00383 |
| Opus 5 | $0.00021 | $0.00192 |
| Sonnet 5 | $0.00008 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
verification-before-completion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Verification Before Completion
Adapted skill — discipline originating in Superpowers v5.1.0 (MIT, Jesse Vincent), rewritten in mattpocock-skills style. The honesty gate in
/mp-implement-issuestep 7 and both pipelines' harvest — no slice counts as done until it passes.
Iron law: no completion or success claim without fresh verification evidence produced in this step. A claim made before its verification is a guess dressed as a fact.
The gate
For each claim you are about to make:
- Name the command that proves it.
- Run that command in full — fresh, in this step.
- Read the complete output and the exit code.
- If the output confirms the claim, make the claim and quote the evidence ("34/34 pass", "exit 0"). If it contradicts the claim, state the actual status with the evidence instead.
Evidence means output from the run you just did. "Should pass", an earlier run, a partial check, a linter where tests are owed, or another agent's self-report are not evidence — a sub-agent's "success" is a lead to verify (check the diff), not a result.
Regression tests
A regression test proves red-green: revert the fix and watch the test fail, restore the fix and watch it pass. A test that never failed proves nothing about the fix.
Requirements
"Tests pass" is not "requirements met". Close out by re-reading the source checklist (issue, spec, plan) and verifying each requirement line by line; report any gap as its actual status.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 30 lines · 42 tokens per session scan A e409549c59a8
verification-before-completion is a skill published in the GitHub repository skywalkercyt/mp-implement (2 stars, last pushed 29d ago), licensed MIT. It adds 42 tokens to every session and 383 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
reversi-master
One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code (Moonshot) ,Qwen Code,Aider,OpenCode,MiMo Code (Xiaomi),ZCode (Z.AI),OpenClaw,Pi,OpenScience,Vibe-Trading,Claude Desktop (3P profile),ChatGPT desktop,OpenCode Desktop.
Trash Talk
AI becomes provocative and mocks the opponent during gameplay.
game-art-direction
Direct game art and creative vision. Turn GAMEDESIGN into a production-level ARTDIRECTION defining a recognizable visual style, camera and composition, world and character grammar, functional colour/light/material, HUD feedback, motion and transition specs, audio direction, and a signature moment for every screen and…
game-build
Build a risk-matched whitebox or the approved production game for its target runtime. Turn GAMEDESIGN, and ARTDIRECTION when production begins, into a minimal BUILDBRIEF and a runnable candidate that can be iterated with replayable evidence. Use for prototype the riskiest design question, implement the approved game…
game-world-design
Design game experience, systems, and levels. Converge the chosen concept into one GAMEDESIGN defining the player promise, core loop, how the world responds, the systems actually needed, level pacing, feedback, failure, and a fully playable prototype. Use for design the game world, deepen the gameplay and levels, write…
novel-game-analyze
Deconstruct a novel for game adaptation. Compress a raw novel, deconstruction library, or writing project into a SOURCEBIBLE with cited textual evidence, extracting world rules, player verbs, spaces, character will, systems, and visual anchors — without inventing a genre yet. Use for gameable book analysis, analyze a…