briefing SKILL.md skillA
briefing from getty/briefing is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add getty/briefing/briefing@git:20261105.25c922aPins git:20261105.25c922a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- getty/briefing
- Path
skills/briefing/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261105.25c922a, committed Nov 5, 2026
- First version recorded
- Sep 23, 2026
- Size
- 10,662 bytes
- Repository stars
- 5
- License
- Artistic-2.0
Author and migrate Claude Code or Codex subagents that use the `briefing` plugin — the spawn-time hook that pre-loads declared skills into the agent's context. Use this skill when adding `briefing.skills` to an agent's frontmatter or a `# briefing: skills = [...]` comment to an agent's TOML, when refactoring an existing agent away from "MANDATORY: load skill X first" prose, or when debugging why a declared skill is not being resolved.
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
# Authoring agents with `briefing` `briefing` pre-loads skills into a subagent's context **before its first turn**. The skill bodies are there the moment the subagent is spawned — no round-trip to load each one, no chance of the model "forgetting". It works in two harnesses, and the difference matters only when you write the declaration: | | Claude Code | Codex | |---|---|---| | Agent file | `.claude/agents/<name>.md` | `.codex/agents/*.toml` | | Declaration | `briefing:` frontmatter block | `# briefing:` comment | | Missing skill | spawn is denied | agent starts, told to abort | This skill tells you how to write agents that use it correctly, and how to convert existing agents that were trying to do this with prompt-stuffed pleas like *"MANDATORY: invoke the brainstorming skill before doing anything else"*. ## The declaration — Codex A Codex agent declares its skills in a comment line: ```toml name = "my_agent" description = "..." # briefing: skills = ["getty-perl-core", "getty-perl-moose", "superpowers:brainstorming"] developer_instructions = """ You are my_agent. Do the thing. """ ``` **Never write a `[briefing]` table.** Codex deserializes agent files …
Read the whole file at its exact version.
How to install
mdr add getty/briefing/briefing@sha256:e9d0297f1f799093The line at the top of this page pins the label git:20261105.25c922a, 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_v7pw43z7v54m6ytx)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 23, 2026 and Nov 5, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261105.25c922a latest | 2026-11-05 | 25c922a | 10,662 B | A | view · diff |
| git:20260927.de9913a | 2026-09-27 | de9913a | 10,666 B | A | view · diff |
| git:20260927.03d0c47 | 2026-09-27 | 03d0c47 | 10,392 B | A | view · diff |
| git:20260924.1f99e64 | 2026-09-24 | 1f99e64 | 10,085 B | A | view · diff |
| git:20260923.6fb3d9a | 2026-09-23 | 6fb3d9a | 9,654 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 (10662 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
getty/briefing · 5 stars · license Artistic-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_v7pw43z7v54m6ytx GET https://markdownregistry.com/api/v1/resolve?ref=getty/briefing/briefing GET https://markdownregistry.com/api/v1/blob/e9d0297f1f7990939809badfb8f5daa2d761f6ce290acafd967f389b0a52e1e2
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.