agentleFS
Kastalien-ResearchKastalien-Research/thoughtbox/.agents/skills/thoughtbox-team/SKILL.md

thoughtbox-team

Skill64 starsChanged 5 months agoMITView on GitHub

Spawn an Agent Team with a background Thoughtbox analyst teammate. The analyst monitors your reasoning sessions for evolution candidates, contradictions, and generates periodic digests. Use this at the start of any deep Thoughtbox reasoning session, when you're about to record many thoughts and want background analysis. Triggers on "start thoughtbox team", "I want a session analyst", "monitor my reasoning", or at the start of any session where you plan to use Thoughtbox extensively.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Use this when you're about to do significant Thoughtbox reasoning — sessions where you'll record 10+ thoughts and want background analysis …

    line 14
  2. Distinctive:

    Don't use this for quick 1-3 thought sessions — the coordination overhead isn't worth it.

    line 16
  3. Very specific:

    Role: Read the agent definition at .Codex/agents/thoughtbox-analyst.md and use it as the teammate's instructions

    line 23
  4. Distinctive:

    Respond to evolution signals: When the analyst says "Thought 55 may contradict thoughts 5, 24", you decide whether to revise.

    line 42
  5. Distinctive:

    Write code or modify files

    line 55
  6. Distinctive:

    When your reasoning session is done, ask the analyst for a final digest, then dismiss the team.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Thoughtbox Team

Spawn a 2-agent team: you (lead) + a background analyst teammate that monitors your Thoughtbox session.

When to Use

Use this when you're about to do significant Thoughtbox reasoning — sessions where you'll record 10+ thoughts and want background analysis of contradictions, evolution candidates, and session digests without having to orchestrate it yourself.

Don't use this for quick 1-3 thought sessions — the coordination overhead isn't worth it.

How to Spawn

Tell Codex you want to create a team. The analyst teammate should be configured with:

  • Name: analyst
  • Role: Read the agent definition at .Codex/agents/thoughtbox-analyst.md and use it as the teammate's instructions
  • Model: Haiku (cost-efficient for background monitoring)
  • Focus: Monitor the Thoughtbox session specified by $ARGUMENTS, or the most recent active session

Example spawn prompt:

Create an agent team with one teammate:
- Name: analyst
- Instructions: [contents of .Codex/agents/thoughtbox-analyst.md]
- Task: Monitor Thoughtbox session [SESSION_ID] for evolution candidates and contradictions. Message me when you find thoughts that should be revised. Generate a digest every 20 thoughts.

Working with the Analyst

Once the team is running:

  1. Do your work normally. Record thoughts via thoughtbox_execute as usual.
  2. Watch for messages. The analyst will message you when it finds evolution candidates.
  3. Respond to evolution signals. When the analyst says "Thought 55 may contradict thoughts 5, 24", you decide whether to revise.
  4. Request digests. Message the analyst: "Give me a digest of where we are."

What the Analyst Does

  • Periodically checks the session for new thoughts
  • Runs deterministic evolution candidate detection (word overlap, structural heuristics)
  • Flags assumption_update and decision_frame thoughts for special attention
  • Generates compressed digests at milestones (~every 20 thoughts)
  • Messages you with concise, actionable findings

What the Analyst Does NOT Do

  • Write code or modify files
  • Apply revisions (it surfaces candidates, you decide)
  • Interrupt for low-signal findings (only messages when overlap > 15%)
  • Access anything outside Thoughtbox sessions

Ending the Session

When your reasoning session is done, ask the analyst for a final digest, then dismiss the team. The digest can be used for session handoff or cross-session context injection.

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.