session-startup
Skill3 starsChanged 20 days agoMITView on GitHub
Obligatory sequence at session start: read AGENTS.md, load phase skills, check memory, run tests and present a plan.
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- architectural-decision-recordsSkill
- conventional-commitsSkill
- gherkin-specsSkill
- git-workflowSkill
- grillingSkill
- implementation-standardsSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-exploreSkill
- openspec-proposeSkill
- openspec-sync-specsSkill
- openspec-workflowSkill
- session-endSkill
- test-driven-developmentSkill
- update-harnessSkill
- using-git-worktreesSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Distinctive: line 30
Present a plan to the user: before touching code.
- Very specific: line 54
When switching roles, announce it as 🎩 Ahora soy <rol> before acting.
≈ “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.
Files
Session startup
The operational contract lives in
AGENTS.md. This skill is the procedure.
Steps (in order)
- Read
AGENTS.md— it is the entry point. If## Commands,## Structureor## Do Not Touchare missing, stop and ask to complete them. - Check the bootstrap state — if
.atlas/state.jsonexists andstatusispending, run.atlas/BOOTSTRAP.mdbefore anything else. Resolve the OpenSpec command preference — read it from
AGENTS.md(§ Preferences):useroragent: no question.ask: ask once at session start: "Do I run the OpenSpec commands this session, or do you?" and apply the answer to this session only.
Combine it with the orchestration question if both are needed.
archiveandsyncalways require explicit approval.- Load the phase skills from the Skill Registry in
AGENTS.md. Do not load skills from packs that are not activated. - Review the previous session — if persistent memory is configured, retrieve the context. If not,
inspect the repo state (
git status,git log -5). - Run the tests with the command declared in
AGENTS.md(## Commands). They must be green before writing code. - Present a plan to the user before touching code.
Workspace check (two phases)
Phase 1 — at startup. Report the current branch, whether the working directory is a worktree and the active change. Informing creates nothing and asks nothing.
Phase 2 — before the first write (a change artifact, code, a QA report or documentation).
Recheck the branch. If it is the base branch, isolate the change with the using-git-worktrees skill or
stop and ask the human. A session that starts in read-only mode still repeats this check before it
writes.
If something is missing
| Missing | Action |
| Test command | Ask; never invent one |
| "Do not touch" rules | Ask before editing |
| Bootstrap pending | Run the ritual first |
| Red tests | Report and do not proceed |
| Writing on the base branch | Isolate or stop; never write on it |
Role announcement
When switching roles, announce it as 🎩 Ahora soy <rol> before acting.
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
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.

