Agent skill
10-init-session-150
[10] INIT. Session-start routine for this project. Use when beginning a new session or onboarding to this repo to load AGENTS.md, MEMORY.md and core project context (README), then summarize context and confirm readiness.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/10-init-session-150
SKILL.md
Init-Session 150 Protocol
Primary workflow
-
Read
AGENTS.mdin the repo root. -
Read
MEMORY.mdin the repo root.- Load Long-Term Memory protocols first.
- Check Lessons (Inbox) and Short-Term for active items.
- Treat Session State as volatile; update it only after confirming with the user.
-
Read core project context files (if present):
README.mdfor project overview and commands.
-
Summarize in 5-8 bullets:
- Most relevant protocols that will affect the upcoming work.
- Any active lessons or warnings.
- Key project constraints (tests, tools, conventions).
-
Ask for confirmation before making changes:
- Confirm the planned next steps.
- Ask whether to update or clear Session State.
Notes
- If any file is missing, state it briefly and proceed with what is available.
- Keep the summary concise; focus on constraints that change behavior.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?