agentleFS
Sign inStart free
YehudaFrankelYehudaFrankel/clankbrain/.claude/skills/start-session/SKILL.md

start-session

Skill16 starsChanged 7 months agoMITView on GitHub

Initialize a working session with full project context. Triggers on \"Start Session\".

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Allowed Tools: Read, Glob, Grep

    line 12
  2. Very specific:

    Read STATUS.md (project root) - get last session summary

    line 18
  3. Very specific:

    Read .claude/memory/MEMORY.md - get current context

    line 19
  4. Very specific:

    If it does NOT exist OR contains "Placeholder": run /scan-codebase immediately.

    line 22
  5. Very specific:

    Read tasks/lessons.md and tasks/regret.md -- refresh on past mistakes and rejected approaches

    line 24

“Common” is measured: kept by at least 6 in 10 of the 6 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

Skill: start-session

Trigger: "Start Session"

Description: Initialize a working session with full project context.

Allowed Tools: Read, Glob, Grep

Steps

  1. Read STATUS.md (project root) - get last session summary
  2. Read .claude/memory/MEMORY.md - get current context
  3. First-session auto-scan (MANDATORY -- do not skip):
    • Glob for .claude/rules/code-map.md
    • If it does NOT exist OR contains "Placeholder": run /scan-codebase immediately. Do not ask, do not report "Ready" first, do not proceed to step 4 until the scan completes and all rule files are written.
    • This is blocking -- the session cannot start without project-specific rules. Generic template files are wrong for most projects and must be replaced by scan-codebase before any work begins.
  4. Read tasks/lessons.md and tasks/regret.md -- refresh on past mistakes and rejected approaches
  5. Report: "Ready. Last change: [summary]. What are we working on?"
  6. One observation (optional, max one line) -- scan recent git log or STATUS.md for something non-obvious worth attention. Examples:
    • "The last 3 sessions all touched the same file -- worth refactoring?"
    • "tasks/error-lookup.md has 3 entries for the same module -- a pattern?"
    • "velocity.md shows this type of task consistently takes 2x the estimate" Skip if nothing stands out. Never more than one line.

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