wgm SKILL.md skillA
wgm from agent-frontier/wgm is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add agent-frontier/wgm/wgm@v0.5.1Pins v0.5.1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- agent-frontier/wgm
- Path
SKILL.md- Versions recorded
- 10
- Latest version
- v0.5.1, committed Oct 18, 2026
- First version recorded
- Aug 24, 2026
- Size
- 41,981 bytes
- Repository stars
- 3
- License
- MIT
Autonomous build skill that turns a rough request into working software through a relentless requirements interview (grill), a persistent plan, and a Ralph-style build loop (analyze → implement → validate → review → record). Use when the user runs /wgm, or asks to build, implement, prototype, or ship a feature or app from rough intent; when a task is ambiguous and needs requirements interrogation before coding; or for multi-step feature work that benefits from a planned, test-validated…
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
# wgm Turn a rough request into working software. `wgm` runs a disciplined lifecycle: `Triage → Grill → Plan → Preflight → Loop(Analyze → Implement → Validate → Review → Record) → Ship/Handoff` It marries three ideas: **grill-me** (interview the human relentlessly until alignment), the **Ralph loop** (one task per iteration, persistent plan as shared state, steered by deterministic backpressure), and **holdout-scenario judging** (after octopusgarden): an LLM judge scores satisfaction against scenarios the build never sees, so a high score can't be gamed. This file is the protocol. Follow it like a state machine — do not skip gates. ## Invocation & modes Invoked as `/wgm [<mode>] [only] [<request>]` — or activated whenever the user asks to build / implement / prototype something from rough intent. **Parse the input first:** 1. Look at the first word. It is a **mode** only if it is exactly one of `grill | analyze | plan | build | loop | review` AND it is followed by end-of-input, the word `only`, or a `:` separator. (`loop` is an alias of `build`.) 2. Otherwise the entire input is the `<request>` and you run the **full lifecycle**. This is the …
Read the whole file at its exact version.
How to install
mdr add agent-frontier/wgm/wgm@sha256:aec0da1ff11c9157The line at the top of this page pins the label v0.5.1, 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.
[](https://markdownregistry.com/a/art_m4lzcvtz2yswiul3)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Aug 24, 2026 and Oct 18, 2026, about one every 6 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.5.1 latest | 2026-10-18 | 33e5f0b | 41,981 B | A | view · diff |
| v0.5 | 2026-10-18 | 895ccad | 41,979 B | A | view · diff |
| v0.5 | 2026-10-18 | 285cfbf | 41,920 B | A | view · diff |
| v0.4 | 2026-10-17 | 80c5ac0 | 41,920 B | A | view · diff |
| v0.4 | 2026-10-17 | 153ae0e | 41,889 B | A | view · diff |
| v0.4 | 2026-09-06 | b13e7b5 | 41,795 B | A | view · diff |
| v0.3 | 2026-08-28 | 06773ef | 41,795 B | A | view · diff |
| v0.3 | 2026-08-24 | 8ce15e0 | 41,854 B | A | view · diff |
| v0.3 | 2026-08-24 | e17d2c9 | 41,847 B | A | view · diff |
| v0.3 | 2026-08-24 | ddf25dd | 41,883 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (41981 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
agent-frontier/wgm · 3 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_m4lzcvtz2yswiul3 GET https://markdownregistry.com/api/v1/resolve?ref=agent-frontier/wgm/wgm GET https://markdownregistry.com/api/v1/blob/aec0da1ff11c91576703e960d601c0664fedf194bf23191a1c0c741e70982e41
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.