agentleFS
Sign inStart free
cathyzhang0905cathyzhang0905/agent-cockpit/skills/brief/SKILL.md

brief

Skill0 starsChanged 7 months agoMITView on GitHub

Output a structured brief at end of plan-worthy tasks. Auto-rendered by Cockpit's Stop hook with adaptive 2-tier format.

78 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use capture, strategy and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • toneron2Skill

    capture

    Capture thoughts to inbox with automatic classification

    Also in 6 projects that use this

  • EpistatesSkill

    strategy

    Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X presence.

    Also in 4 projects that use this

  • aleksander-dytkoSkill

    decision

    Make a product decision with full context from the vault and available sources

    Also in 3 projects that use this

  • dirienSkill

    decide

    Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.

    Also in 5 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 7 projects that use this

  • howellsSkill

    reconcile

    Audit a project against current plugin conventions and offer to update structure.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 71 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before finishing your response on a plan-worthy task, output a <cockpit-brief> block.

    line 12
  2. Distinctive:

    If you forget the brief block, the user sees no structured summary — degraded UX but not broken.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 71 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Brief

Cockpit's third principle: every plan-worthy task ends with a structured brief that surfaces what was decided and what's worth review. Solves spec.md §2 FM3 (post-execution attribution gap).

Behavior

Before finishing your response on a plan-worthy task, output a <cockpit-brief> block. Format adapts to task complexity (mirrors plan tier).

Tier 1 — Simple task

<cockpit-brief>
Done in ~Tmin. N decisions. Output: PATH
</cockpit-brief>

Tier 2 — Detailed task

<cockpit-brief>
Decisions made: N
Outputs: [list of paths or deliverables]
Time taken: ~Tmin
Recommend review: [1-2 decisions worth re-examining, or omit if none]
</cockpit-brief>

The Recommend review field is the soul of Tier 2 brief — agent flags its own uncertainty for the user.

Why this exists

Without a brief, users see the final output but can't easily trace back to which decision caused which result. With a brief:

  1. Scoped summary of what was decided
  2. Pointer to specific decisions worth reviewing (agent self-flags risk)
  3. List of artifacts produced

Connection to decision log

The brief is the human-facing summary. The full audit trail lives in ./.cockpit/[date].jsonl (written by PostToolUse hook).

JSONL schema is compatible with disler/claude-code-hooks-multi-agent-observability event format — users can run Cockpit + disler dashboard together for retrospective analysis.

Behavior is hook-driven

Stop hook parses the transcript for <cockpit-brief> block and renders it in a Unicode-bordered box. Trivial tasks (Haiku judge → skip) get no brief.

Failure mode

If you forget the brief block, the user sees no structured summary — degraded UX but not broken. The decision log JSONL still records every tool call.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free