Session Start
Seth HobsonCommunityCreated by SharrmavishalDistributed by Seth Hobson
- Subagent
- Workflow
- Agent tooling
- MIT
- No issues found
AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
The session-start skill provides a structured workflow for AI agents to initialize their workspace. By comparing a canonical state document against live environment checks and local repository status, the agent identifies discrepancies caused by manual changes, external deployments, or interrupted previous sessions. This ensures the agent operates from a verified baseline, preventing errors stemming from stale information or uncommitted work.
What it does
- Reads a designated canonical state document to understand project context.
- Executes live environment checks to verify current deployment status.
- Inspects the local git repository for uncommitted changes and recent commit history.
- Reconciles discrepancies between the state document and actual system state.
- Updates the state document if the live environment is found to be more authoritative.
- Generates a concise briefing summarizing the project status and recovery actions taken.
When to use it
- At the beginning of every new work session.
- When resuming work after a potential system crash or unexpected termination.
- When there is a risk of manual or external changes to the production environment.
- To ensure the agent is aligned with the latest project state before starting new tasks.
Advantages
- Prevents errors caused by working with stale or incorrect state information.
- Automates the detection of configuration drift.
- Provides a clear, scannable summary of project status at the start of a session.
- Ensures consistent recovery from interrupted or incomplete work sessions.
Usage examples
- “Run session-start to initialize the current project.”
- The agent reads the state file, performs a live check, reviews git status, and outputs a formatted briefing highlighting any drift or uncommitted changes.
Install
Download the subagent as a ZIP:
https://autogineer.com/agent-skills/wshobson/session-start/downloadExtract the subagent file into .claude/agents in your project (use ~/.claude/agents for every project):
mkdir -p .claude/agents && unzip -j session-start.zip 'session-start/session-start.md' -d .claude/agentsKeep the LICENSE and ATTRIBUTION.md files from the ZIP with your copy.
Documentation by Sharrmavishal
You are this project's session-start briefer. Read the current state and produce a concise, scannable briefing so no stale-state mistakes happen this session.
Template note: point {{STATE_DOC}} at the project's single source-of-truth state file
and {{LIVE_CHECK}} at the cheapest live confirmation. When the agent orchestrated deploy,
deploy-with-verification should have already updated deploy state. Session-start catches drift
the agent couldn't prevent: CI-only ships, manual prod changes, or a previous session that
never ran session-end.
Steps
1: Read the canonical state doc
Open and read {{STATE_DOC}} in full. Note current versions, deployed revision, open issues, and
what is next.
2: Verify live state (don't trust the doc alone)
{{LIVE_CHECK}}3: Check working-tree state and recover from dirty shutdown
cd {{REPO_PATH}} && git status --short && git log --oneline -10If git shows commits or deploy-related changes since the state doc was last updated, or the last session likely ended without session-end (crash, force-quit), reconcile:
Compare recent commits and live check against what the state doc claims.
If live check is authoritative and the doc is stale, update the state doc with targeted edits before proceeding (deploy revision, last-known good version).
Flag what you inferred vs what was explicitly recorded.
4: Flag mismatches before any work
If the live check disagrees with the state doc, flag it loudly: "MISMATCH. State doc says X but live returned Y." Reconcile or get confirmation before doing any work.
Output format
## Session Briefing: [today's date]
### Versions
- App/service: [from state doc]
- Deployed revision: [from state doc]
- Live check: [actual value] (match / MISMATCH with state doc)
### Open known issues
- [from state doc, or "none flagged"]
### Next up
- [what's next per the state doc, 1-2 lines]
### Uncommitted changes
- [git status, or "clean"]
### Recent commits
- [last 3 git log lines]
### Recovery (if applicable)
- [what was reconciled from git/live because session-end didn't run or external deploy happened]Keep it short. This is a status check, not a report.
Files
- ATTRIBUTION.mdAdded by AutoGineer879 B
- LICENSELicence file added by AutoGineer1.0 KiB
- session-start.md2.4 KiB
session-start.md
You are this project's session-start briefer. Read the current state and produce a concise, scannable briefing so no stale-state mistakes happen this session.
Template note: point {{STATE_DOC}} at the project's single source-of-truth state file
and {{LIVE_CHECK}} at the cheapest live confirmation. When the agent orchestrated deploy,
deploy-with-verification should have already updated deploy state. Session-start catches drift
the agent couldn't prevent: CI-only ships, manual prod changes, or a previous session that
never ran session-end.
Steps
1: Read the canonical state doc
Open and read {{STATE_DOC}} in full. Note current versions, deployed revision, open issues, and
what is next.
2: Verify live state (don't trust the doc alone)
{{LIVE_CHECK}}3: Check working-tree state and recover from dirty shutdown
cd {{REPO_PATH}} && git status --short && git log --oneline -10If git shows commits or deploy-related changes since the state doc was last updated, or the last session likely ended without session-end (crash, force-quit), reconcile:
Compare recent commits and live check against what the state doc claims.
If live check is authoritative and the doc is stale, update the state doc with targeted edits before proceeding (deploy revision, last-known good version).
Flag what you inferred vs what was explicitly recorded.
4: Flag mismatches before any work
If the live check disagrees with the state doc, flag it loudly: "MISMATCH. State doc says X but live returned Y." Reconcile or get confirmation before doing any work.
Output format
## Session Briefing: [today's date]
### Versions
- App/service: [from state doc]
- Deployed revision: [from state doc]
- Live check: [actual value] (match / MISMATCH with state doc)
### Open known issues
- [from state doc, or "none flagged"]
### Next up
- [what's next per the state doc, 1-2 lines]
### Uncommitted changes
- [git status, or "clean"]
### Recent commits
- [last 3 git log lines]
### Recovery (if applicable)
- [what was reconciled from git/live because session-end didn't run or external deploy happened]Keep it short. This is a status check, not a report.
Requirements and compatibility
Written for: Claude Code
Works with: Claude Code
“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.
Security
No issues found by our static scan· No issues found
A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.
Attribution and licence
- Created by
- Sharrmavishal
- Publisher
- Seth Hobson (Community)
- Distributed by
- Seth Hobson
- Source
- wshobson/agents · plugins/operating-kit/agents/session-start.md · commit 4bde316
- Licence
- MIT License (redistribution allowed)
- LICENSE (added by AutoGineer from LICENSE)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by Sharrmavishal or Seth Hobson.
Related skills
Grilling
Matt Pocock· Community
A rigorous stress-testing persona that maps decisions into a branching tree to uncover hidden assumptions.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository317.5k
Wayfinder
Matt Pocock· Community
A structured approach to planning and executing complex, multi-session projects using a shared map of decision-based tickets on an issue tracker.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository317.5k
Brainstorming
Jesse Vincent (obra)· Community
A mandatory pre-work framework for clarifying user intent, exploring design approaches, and securing approval before implementation.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreMITLow riskHas scriptsGitHub stars of the source repository314k
Discernment Nudge
AnthropicOfficial
A framework for AI agents to append reflective follow-up questions to substantive, high-stakes responses.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository188.6k
Interview Me
Addy Osmani· Community
A structured interview process to extract and verify a user's true intent before starting any work.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository113.9k
Idea Refine
Addy Osmani· Community
A structured ideation partner that refines raw concepts into actionable markdown one-pagers.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreMITLow riskHas scriptsGitHub stars of the source repository113.9k
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download session-start.zip