Require fresh, scope-appropriate evidence before any completion claim. Distinguishes implemented, locally verified, repository-green, PR-green, deployed, and observed-stable states.
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
Completion is a claim about observed state, not effort or confidence.
- Use the repository's real verification commands (manifests, CI, project
docs) — never invented generic ones. Baseline before substantive edits
when practical; separate pre-existing failures from regressions.
- Run fresh, applicable checks after the final relevant edit. Later edits
invalidate earlier evidence for the affected gates — re-run them.
- A failing check is work to diagnose and repair. Never delete, skip,
narrow, mock away, blanket-update, or silence the behavior under test to
obtain green output.
- During a present-then-stop `audit-*` or `plan-*` pass, record failing
checks as findings. Do not implement fixes unless the user asked to
execute.
- If a check is unavailable, report `not run` with the concrete reason.
Missing evidence is never a pass.
Claim only the highest level actually proven:
**implemented → scoped verified → repository green → PR green → deployed
verified → observed stable.** Do not call work "done", "shipped", "green",
or "stable" above the evidence.
## Delivering work
…
The line at the top of this page pins the label git:20260923.cf348bd, 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.
A 14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Size between 200 bytes and 200 KB (3099 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
kensaurus/skills · 9 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2bc65q6mvvojlpjq
GET https://markdownregistry.com/api/v1/resolve?ref=kensaurus/skills/.cursor/rules/verification-before-completion.mdc
GET https://markdownregistry.com/api/v1/blob/e950a3414006393bbec37d2581e11f8e1d437e697ec64438005a7f60a7c0b0da
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.
kensaurus/skills · .cursor/rules/approved-plan-execution.mdc · Guard execution of an approved plan or burndown: forbid reward hacking and feature deletion; require checkpoints…
kensaurus/skills · skills-cursor/canvas/SKILL.md · Create a live React canvas beside chat for standalone analytical artifacts that benefit from visual layout…
kensaurus/skills · skills-cursor/create-hook/SKILL.md · Create Cursor hooks. Use to create a hook, write hooks.json, add hook scripts, or automate behavior around agent events.
kensaurus/skills · skills-cursor/create-rule/SKILL.md · Create Cursor rules for persistent AI guidance. Use when user wants to create a rule, add coding standards, project…
kensaurus/skills · skills-cursor/create-skill/SKILL.md · Guide users through creating effective Agent Skills for Cursor. Use when user wants to create, write, update, or debug…
kensaurus/skills · skills-cursor/create-subagent/SKILL.md · Create custom subagents for specialized AI tasks. Use when the user wants to create a new type of subagent, set up…
kensaurus/skills · skills-cursor/shell/SKILL.md · Run the rest of a /shell request as a literal shell command. Use only when the user explicitly invokes /shell and wants…
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…
