verify SKILL.md skillA

verify from bmtrnavsky/disciplined-vibe-coding is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add bmtrnavsky/disciplined-vibe-coding/verify@git:20261027.5b28691

Pins git:20261027.5b28691 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
bmtrnavsky/disciplined-vibe-coding
Path
skills/verify/SKILL.md
Versions recorded
3
Latest version
git:20261027.5b28691, committed Oct 27, 2026
First version recorded
Sep 13, 2026
Size
2,267 bytes
Repository stars
14
License
a license file GitHub does not identify

Use before done-claims, milestone completion, releases. Fresh evidence — terminal, user-attested, integrity, plus metric-band handling for nondeterministic work. Compact report, full table in plan, milestone retain. (Lineage: godmode/completion-gate, superpowers/verification-before-completion).

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

# Verify — evidence or it didn't happen

## Prime directive
Nothing is done until fresh evidence, read in full, proves it.

## Steps (in order)
1. **Re-run, fresh.** Plan checks now; earlier output describes earlier code.
2. **Classify evidence honestly:**
   - *Terminal:* commands re-run this session.
   - *User-attested:* User-run checks; labeled, never simulated.
   - *Integrity:* data tasks — counts, checksums, sampled diffs, dry-run vs live. Zero-exit with wrong numbers FAILED.
   - *Metric:* model/eval tasks — compare against the plan's metric band. Nondeterministic runs: re-run with fixed seed where possible; report the observed values AND the band, honestly — "0.819 vs target 0.82" is a NEAR MISS to escalate, not a pass to fudge.
3. **Read all output.** Truncated → file → review. Skipped suites fail.
4. **Report compact, store complete.** "14 of 14 (10 terminal, 2 user, 1 integrity, 1 metric-in-band.)" Failures full. Table to plan file; one-liner rung has no plan file, so the chat summary IS the stored report.
5. **Milestone close:** mark complete; retain summary (shipped/decided/established) to Hindsight.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add bmtrnavsky/disciplined-vibe-coding/verify@sha256:baa04b80730fbb7b

The line at the top of this page pins the label git:20261027.5b28691, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_doz3jwtddnefqjxe.svg)](https://markdownregistry.com/a/art_doz3jwtddnefqjxe)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Sep 13, 2026 and Oct 27, 2026, about one every 22 days.

versioncommittedcommitsizeaudit
git:20261027.5b28691 latest2026-10-27 5b28691 2,267 BA view · diff
git:20261027.93e47a52026-10-27 93e47a5 2,263 BA view · diff
git:20260913.7de97942026-09-13 7de9794 2,188 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2267 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

bmtrnavsky/disciplined-vibe-coding · 14 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_doz3jwtddnefqjxe
GET https://markdownregistry.com/api/v1/resolve?ref=bmtrnavsky/disciplined-vibe-coding/verify
GET https://markdownregistry.com/api/v1/blob/baa04b80730fbb7b345ceb9cc29cfc848265a38bc6baff2f9314e8343ea19cfe

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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from bmtrnavsky/disciplined-vibe-coding

disciplined-vibe-coding SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · plugins/disciplined-vibe-coding/SKILL.md · Run any coding task through Intake, Define, Economy gate, Plan, Teardown, Build, Verify, Commit — with Wayfinder…
v0.2.0 · audit A · 14 stars
brainstorm SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/brainstorm/SKILL.md · Use after intake when a confirmed direction has approach-level design choices. 2-3 options per fork, batch independent…
git:20261027.93e47a5 · audit A · 14 stars
debug SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/debug/SKILL.md · Use whenever behavior is wrong, tests fail, or the user reports a bug. Docs-first root-cause triage, observation mode…
git:20261027.93e47a5 · audit A · 14 stars
execute SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/execute/SKILL.md · Use in Build to run an approved plan. Direct work or up to 5 workers; orchestrator exclusively owns git, plan/roadmap…
git:20261027.93e47a5 · audit A · 14 stars
intake SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/intake/SKILL.md · Use at the very start of any coding task or project. Interviews, classifies scale AND stakes, resolves direction forks…
git:20261027.5b28691 · audit A · 14 stars
plan SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/plan/SKILL.md · Use to plan one milestone (or small task) into atomic steps: paths, outputs, pass/fail checks, rollback/dry-run for…
git:20261027.5b28691 · audit A · 14 stars
research SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/research/SKILL.md · Use before building anything novel, modifying unfamiliar code, ranking unfamiliar tech, or whenever a library/API is…
git:20261027.93e47a5 · audit A · 14 stars
test-first SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/test-first/SKILL.md · Use during Build for testable logic. Failing test before implementation (light RGR). Declared exemptions over faked…
git:20261027.93e47a5 · audit A · 14 stars
version SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/version/SKILL.md · Use for commits at Build checkpoints, and releases/bumps/changelogs in Verify. Narrative commits, semver…
git:20261028.1e22c39 · audit A · 14 stars
write-docs SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/write-docs/SKILL.md · Use whenever writing docs/notes/changelogs/plans/roadmaps/prose for the user. Pragmatic ASD-STE100. Governs question…
git:20261027.93e47a5 · audit A · 14 stars

Every file in bmtrnavsky/disciplined-vibe-coding

Other files named verify

verify SKILL.md skill
garrytan/gstack · verify/SKILL.md · Use when coding: run the checks and tests /ship picks until green. (gstack)
v0.1.0 · audit A · 138,879 stars
verify SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/verify/SKILL.md · Verify that a change really works before you claim completion
git:20260401.ff9223c · audit A · 40,492 stars
verify SKILL.md skill
zenbu-labs/terminal-browser · .claude/skills/verify/SKILL.md · Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video +…
git:20260721.c3339dc · audit A · 4,376 stars
verify SKILL.md skill
alsk1992/cloddsbot · src/skills/bundled/verify/SKILL.md · Verify agent identity using ERC-8004 on-chain registry
git:20260130.5926fbf · audit A · 3,052 stars
verify SKILL.md skill
ethanyoq/ai-novel-writer · .claude/skills/verify/SKILL.md · 在真实 Electron 中驱动 AI 小说作家,按场景截图、记录启动耗时并读取只读诊断。前端重设计 RD-0 至 RD-10 每个 PR 的实机验证都走这里。用于「实机验证」「截图对比」「跑一下界面场景」。
git:20261028.6a56326 · audit B · 2,254 stars
verify SKILL.md skill
zereight/gitlab-mcp · .github/skills/verify/SKILL.md · Verify that a change really works before claiming completion. Activate when user says: verify this, check if it works…
git:20260412.9d9ce51 · audit A · 2,080 stars
verify SKILL.md skill
codeaholicguy/ai-devkit · skills/verify/SKILL.md · AI DevKit · Enforce evidence-based completion claims — require fresh command output before reporting success. Use when…
git:20261028.9c55339 · audit A · 1,656 stars
verify SKILL.md skill
sethgammon/citadel · skills/verify/SKILL.md · Self-test the Citadel hook pipeline from within a live session. Exercises real tool calls (Write, Edit, Bash, Read) and…
git:20260919.f58febd · audit A · 929 stars

Browse by kind, by grade A, or by owner.