Session open
A curated collection of reusable AI agent skills, playbooks, and prompts for security audits, engineering workflows, and automation.
npx -y skills add vishnujchandran/.agents --skill session-openAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Restart-safe session starter that restores context, validates readiness, and creates a focused execution plan for the current development session.
SKILL.md
1.9 KB, 387 tokens by cl100k_base, as published. Nobody here has run it
session-open (v2.0)
Open a development session with enough structure that work can resume quickly without re-discovery overhead.
Trigger Signals
Use when user asks to:
- start today’s coding session
- continue from where we stopped
- recover context after interruption
- define focus for current session
Inputs
- optional: previous checkpoint file (
SESSION_CHECKPOINT.mdor equivalent) - optional: current branch / open PR / issue ID
- optional: available work window (e.g., 30m, 2h)
Workflow
- Load latest checkpoint or reconstruct from recent changes/tasks.
- Summarize restored context (what, why, current state).
- Validate context completeness (missing details, blockers, assumptions).
- Define session objective + done criteria.
- Create prioritized plan (P0/P1/P2) with first 3 executable actions.
- Produce restart artifact for current session start.
Context Completeness Score
Score 0–5 and explain missing pieces:
- 0–1: missing critical context
- 2–3: partial context, proceed with caution
- 4–5: ready to execute
Output Contract
Return exactly:
- Restored context summary
- Context completeness score + missing info
- Session objective + done criteria
- Prioritized tasks (P0/P1/P2)
- Immediate next 3 actions
- Risks/blockers
Fail Conditions
Mark result as blocked if:
- no clear objective can be defined
- critical dependency/access/context is missing
- conflicting priorities cannot be resolved
Templates
Use templates/session-open-template.md for consistent output.
Guardrails
- Keep scope realistic for one session
- Prefer concrete actions over broad planning
- State assumptions explicitly
- Never fabricate restored context