Use when preparing to say a change is complete, a defect is fixed, checks pass, or a commit or release is ready.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Verification Before Completion
Match each completion claim to fresh evidence from the current revision. This
skill checks the claim; it does not replace a task contract, QA plan, or the
project's test procedure.
## Check the claim
1. Write down the exact behavior or state you intend to report.
2. Select the smallest relevant verification channel: automated test, build,
manual reproduction, artifact inspection, or explicit user acceptance.
3. Run or inspect that channel after the last relevant edit. Record the command
or manual steps, target revision, result, and any skipped scope.
4. Compare the result with the claim. A passing linter does not prove a build;
a passing build does not prove behavior; a changed file does not prove a bug
is fixed.
5. Report only what the evidence supports. If verification is unavailable,
identify the unverified claim and the specific blocker.
For a defect, repeat the original failing scenario after the fix. For a tracked
task, check each required acceptance criterion and use its owning lifecycle
skill for status changes. User acceptance is valid evidence when the workflow
allows it; do not demand a log or screenshot to replace it.
…
The line at the top of this page pins the label git:20261008.93495d3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_46h4rnaevxckk74k
GET https://markdownregistry.com/api/v1/resolve?ref=furkantokkan/agent-foundry/verification-before-completion
GET https://markdownregistry.com/api/v1/blob/e1b1be29422468b2ecc34fc4e1812167c8c9f034d3ad7e56e0ebaae2ca7380b1
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
furkantokkan/agent-foundry · plugins/agent-foundry/skills/adaptive-skills/SKILL.md · Use when a task may span multiple personal skills and Codex should choose the smallest relevant skill set across Unity…
furkantokkan/agent-foundry · plugins/agent-foundry/skills/agent-orchestration/SKILL.md · Coordinate game, Unity, web, SaaS, and tooling work through one orchestration workflow across Claude and Codex. Resolve…
furkantokkan/agent-foundry · plugins/agent-foundry/skills/architecture-decision/SKILL.md · Creates an Architecture Decision Record (ADR) documenting a significant technical decision, its context, alternatives…
furkantokkan/agent-foundry · plugins/agent-foundry/skills/architecture-review/SKILL.md · Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix…
furkantokkan/agent-foundry · plugins/agent-foundry/skills/art-bible/SKILL.md · Guided, section-by-section Art Bible authoring. Creates the visual identity specification that gates all asset…
furkantokkan/agent-foundry · plugins/agent-foundry/skills/asset-audit/SKILL.md · Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline…
furkantokkan/agent-foundry · plugins/agent-foundry/skills/asset-spec/SKILL.md · Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles…
furkantokkan/agent-foundry · plugins/agent-foundry/skills/balance-check/SKILL.md · Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate…
furkantokkan/agent-foundry · plugins/agent-foundry/skills/brainstorm/SKILL.md · Guided game concept ideation — from zero idea to a structured game concept document. Uses professional studio ideation…
furkantokkan/agent-foundry · plugins/agent-foundry/skills/bug-report/SKILL.md · Creates a structured bug report from a description, or analyzes code to identify potential bugs. Ensures every bug…
furkantokkan/agent-foundry · plugins/agent-foundry/skills/bug-triage/SKILL.md · Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic…
obra/superpowers · skills/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running…
mvschwarz/openrig · packages/daemon/specs/agents/shared/skills/process/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running…
mvschwarz/openrig · skills/_canonical/process/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running…
a5c-ai/babysitter · library/methodologies/superpowers/skills/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Evidence before…
a5c-ai/babysitter · library/methodologies/cc10x/skills/verification-before-completion/SKILL.md · Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success…
ganyuanran/aegis · skills/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish…
coco-research/coco · skills/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running…