agentleFS
Sign inStart free
MetaMindTeamMetaMindTeam/ssot-kit/.claude/skills/start-session/SKILL.md

start-session

Skill1 starsChanged 4 months agoApache-2.0View on GitHub

Start a work session on this project. Loads project state from disk — changelog, open tasks, and the spec of the current task — so the session resumes from ground truth. Use at the beginning of every 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

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Follow the canon's session discipline (spec/standards/spec_driven_standard.md).

    line 11
  2. Very specific:

    uninitialized project: If a brief is present (passed, or a *.md brief in the repo), route to init-project (or spec) instead of resuming — …

    line 16
  3. Very specific:

    Load the relevant spec: Read the spec/ files that the current task touches *before* writing any code.

    line 22

“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

start-session

Follow the canon's session discipline (spec/standards/spec_driven_standard.md).

  1. Detect state first. Uninitialized markers: CLAUDE.md still holds <...> placeholders, or spec/domain/entities.yaml has only the Example stub (no real product nouns), or spec/features/ holds only kit modules (_example, continuity, enforce). Any of these → uninitialized project. If a brief is present (passed, or a *.md brief in the repo), route to init-project (or spec) instead of resuming — don't spend a session asking "how does the framework work". State this and proceed.
  2. Read the changelog. Open CHANGELOG.md, read the most recent entries.
  3. Find active work. List spec/features/*/spec.yaml with status: approved or in-progress. If one is unfinished, that's your resume point.
  4. Load the relevant spec. Read the spec/ files that the current task touches before writing any code.
  5. State the plan. Summarize where the project is and what you'll do next.

Invariant: every session resumes from disk, not from memory. Uninitialized + brief present → init-project, not a Q&A about the framework.

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