agent-brief — Claude Code skill: what it does, how to install
The agent-brief skill for Claude Code structures task delegation to AI agents. It forces clarity on stakes, hypotheses, and verification criteria before an agent starts working.
MIT ★ 741 updated 2026-11-11
/plugin marketplace add MiniMax-AI/mcode-stack
/plugin install ronny@mcode-stackWhat agent-brief does
This tool establishes a mandatory planning phase before handling complex coding tasks. Users fill out a structured brief covering the impact of the task, expected outcomes, scope constraints, and concrete verification steps. Clear documentation prevents agents from filling in gaps with assumptions that differ from the user's intent.
The brief forces a choice between collaborative thinking or full delegation. If asking the agent to work independently, the user commits to a more rigorous final review. This structured approach reduces debugging time since the definition of success is established before code is written.
The tool runs locally and requires no external API keys or subscriptions. To install in Claude Code, run /plugin marketplace add MiniMax-AI/mcode-stack followed by /plugin install ronny@mcode-stack.
What it helps with
- define hypothesis before starting
- set verification criteria before seeing output
- differentiate between collaborative and autonomous modes
- prevent agent from guessing implementation details
Example prompts for the agent
- agent-brief: start a new brief
- Apply the agent-brief template to this ticket
- Fill out the brief for stakes, hypothesis, and goal
How to install agent-brief
1Plugin marketplace
/plugin marketplace add MiniMax-AI/mcode-stack/plugin install ronny@mcode-stackThis installs the whole ronny plugin with all its skills
2Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill agent-brief -a claude-code3Manually: put the files in place
~/.claude/skills/agent-brief/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/agent-brief/
1Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill agent-brief -a codex2Manually: put the files in place
.agents/skills/agent-brief/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill agent-brief -a cursor2Manually: put the files in place
.cursor/skills/agent-brief/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install MiniMax-AI/mcode-stack stacks/ronny/skills/agent-brief2Manually: put the files in place
.github/skills/agent-brief/SKILL.md1Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill agent-brief -a gemini-cli2Platform CLI
gemini skills install https://github.com/MiniMax-AI/mcode-stack --path stacks/ronny/skills/agent-briefManually: put the files in place
.devin/skills/agent-brief/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about agent-brief
How to install agent-brief in Claude Code?
Run /plugin marketplace add MiniMax-AI/mcode-stack followed by /plugin install ronny@mcode-stack.
What does agent-brief do?
It provides a template and structure for briefing AI agents on task stakes, user hypotheses, goals, and success verification.
What is required to use agent-brief?
It is a local skill requiring no additional API keys or paid services.
Source text
SKILL.md · MIT
--- name: agent-brief description: Write the brief before handing a non-trivial task to an agent or subagent, covering stakes, your own hypothesis, goal and scope in your words, what "verified" will mean, and whether the agent is thinking with you or for you. Use before starting a MiniMax Code session, spawning a subagent, or delegating a PR, analysis or doc. --- # Agent Brief We delegate a lot. What we try not to delegate is knowing what we asked for. If we cannot write the task down in a few plain lines, the idea is not ready, and the agent will fill the gaps with defaults we never chose. Five minutes here saves a review that cannot tell right from plausible. ## 1. Set the stakes Decide how much of this skill to run. - **Cheap to be wrong**: a throwaway script, a rename, formatting, a local experiment we will delete. Hand it off and skip the rest. - **Someone else lives with it**: code that ships, a change to the harness, anything touching users, money, permissions or data, a number that goes into a decision. Run every step, and plan to use `evidence-first-review` after. When unsure, ask: if this is quietly wrong, who finds out, and when? ## 2. Write a hypothesis first One line on what we expect the answer or the fix to be, written before the agent starts. A wrong guess is fine. Its job is to give us something to compare against, so a polished answer does not become the default. > Hypothesis: the flaky `compaction.e2e` test is a race between the summary > write and the next turn, not a model issue. ## 3. Brief in our own words - **Goal**: the outcome, not the steps. - **Who uses it**: a reviewer, a user, another agent. - **Out of scope**: what it must not touch (public API, lockfile, other packages). - **Constraints**: versions, style, files it may edit, commands it may run. If we get stuck writing this, we ask the agent to interview us first, or give it what we know and ask what we have not thought of. We do not ask it to write the brief for us. ## 4. Define "verified" before seeing output Pick something we can check later, decided now so we cannot bend it to fit whatever comes back: - a named test passes, and a new test fails on the old code; - a command and its expected output (`mcode -p "..." --json` returns X); - a screenshot or log line from the real app; - a number recomputed from the source data. Give the agent the same means to check itself (test command, fixture, a running dev server), so it loops before we look. ## 5. Name the mode Are we asking it to help us think, or to think for us? Both are fine. In the second case, we owe a stricter review, because we will not have the reasoning in our heads. ## Card Paste this at the top of the task: ```text Stakes: low | high Hypothesis: ... Goal / users / out of scope: ... Done = (tangible check): ... Mode: think with me | do it for me When done: show commands run and their output first, then the summary, then the decisions and assumptions you made. ``` ## References - Addy Osmani, ["Critical thinking when agents do the work"](https://x.com/addyosmani/status/2117512471930167377)
© Ronny (MiniMax Code team) · MIT · MiniMax-AI/mcode-stack