session-start
Skill0 starsChanged 7 months agoMITView on GitHub
Use this skill at the start of every session to load context from Hindsight and orient in the codebase with CGC. Run before any task.
39 other projects use a version of this.
Adopted by
Most recently taken up by
- kimkon1011/orgiast-claude-rulestheir own version, first seen Nov 8, 2026
- salvo8519/fairmarktheir own version, first seen Nov 8, 2026
- jaywedgeworth22/BotFleettheir own version, first seen Nov 3, 2026
- Simple-With-Us/BotFleettheir own version, first seen Nov 3, 2026
- desertcache/agent-ostheir own version, first seen Nov 1, 2026
- ravindu57/SCMLtheir own version, first seen Nov 1, 2026
Used with
Projects with it also use session-end, deploy-verify and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
jasonmichaelbell78-creatorSkillsession-end
Also in 11 projects that use this
danielarif26Skilldeploy-verify
Verify a Vercel deployment actually went live and serves the correct production domain. Self-improving: reads its own run history before checking and logs the outcome after. Use when the user asks "did you deploy?", "is it live?", "verify the deploy", "check vercel", or after any Vercel deploy. Part of the Agentic OS (Level 1 backbone).
Also in 3 projects that use this
Microsoft AzureSkillreflect
Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.
Also in 4 projects that use this
ibahgatSkillautopilot
Run autonomous multi-stage execution loops until acceptance criteria pass or blockers are reached.
Also in 3 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions39 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 39
- bitwize-music-studio/claude-ai-music-skills★ 589same name
- AlexZio00/sovereign-skills★ 157same name
- yahor-punko/mavericks-os★ 89same name
- Kanevry/session-orchestrator★ 53same name
- xcota/pos★ 32same name
- iamneilroberts/claude-skills★ 26same name
- albertomarturelo/sii★ 18same name
- IlyaGorsky/memory-toolkit★ 13same name
- mae616/ai-template★ 9same name
- freskhu/genesis★ 5same name
29 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/tta-dev.mdcCursor rule
- build-test-verifySkill
- core-conventionsSkill
- create-atomic-noteSkill
- create-pull-requestSkill
- git-commitSkill
- sdd-workflowSkill
- self-review-checklistSkill
- build-test-verifySkill
- core-conventionsSkill
- create-agentSkill
- create-atomic-noteSkill
- create-pull-requestSkill
- Feature DevelopmentSkill
- git-commitSkill
- Incident ResponseSkill
- Package ReleaseSkill
- sdd-workflowSkill
- self-review-checklistSkill
- session-startSkill
- ttadev-llmSkill
- ttadev-primitivesSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 32 edited versions we read keep these.
4
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
- Distinctive: line 8
Run these steps at the beginning of every session, before any task work.
- Distinctive: line 20
Read all results. The global bank carries durable user/workflow rules.
- Distinctive: line 28
Read all results. This is your architectural map.
- Very specific: line 38
Call mcp__codegraphcontext__get_repository_stats to confirm the graph is current.
- Very specific: line 40
If the task involves specific files/functions, also call mcp__codegraphcontext__find_code for the target to understand its position in the …
- Very specific: line 50
Before ending the session or after completing a significant task, call mcp__hindsight__retain with the appropriate bank and content …
- Distinctive: line 55
Use this format for the content:
“Common” is measured: kept by at least 6 in 10 of the 32 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.
Files
Session Start Protocol
Run these steps at the beginning of every session, before any task work.
1. Load directives
Call mcp__hindsight__recall with:
- bank_id:
adam-global - query:
durable directives preferences workflow defaults coding standards model strategy
Then call mcp__hindsight__recall again with:
- bank_id: the current derived
project-*orworkspace-*bank - query:
repository conventions architecture commands failures patterns
Read all results. The global bank carries durable user/workflow rules; the project/workspace bank carries repository-specific context.
2. Load mental models
Call mcp__hindsight__recall with:
- bank_id: the current derived
project-*orworkspace-*bank - query:
mental model primitives agents workflows integrations architecture
Read all results. This is your architectural map.
3. Recall task-specific context (if task is known)
Call mcp__hindsight__recall with:
- bank_id: the current derived
project-*orworkspace-*bank - query:
<the specific module, feature, or component you are about to work on>
4. Orient with CGC
Call mcp__codegraphcontext__get_repository_stats to confirm the graph is current.
If the task involves specific files/functions, also call mcp__codegraphcontext__find_code
for the target to understand its position in the graph.
5. Acknowledge
State briefly what you loaded — directives active, mental models loaded, current graph stats — so the user knows the session started warm.
Session End: Retain
Before ending the session or after completing a significant task, call
mcp__hindsight__retain with the appropriate bank and content covering:
adam-globalfor durable cross-project preferences or reusable workflow patterns- the current derived
project-*orworkspace-*bank for repository-specific decisions, failures, commands, and architectural insights
Use this format for the content:
[type: decision|pattern|failure|insight] <what happened>
Rationale/why: <the reason>
Context: <module or area affected>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.