agentleFS
cwinvestmentscwinvestments/memstack/skills/state/SKILL.md

state

Skill425 starsChanged 5 months agoMITView on GitHub

Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.

8 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use discover and delegate.

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.
  • anombyte93Skill

    discover

    Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

    Also in 3 projects that use this

  • scott2bSkill

    delegate

    Intelligently analyzes tasks and delegates them to the most appropriate AI system when delegation adds value (project, gitignored)

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When this skill activates, output:

    line 13
  2. Distinctive:

    If found, read it and present a brief summary:

    line 38
  3. Distinctive:

    If not found, say: "No STATE.md exists yet.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 6 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

📍 State: Updating Project State...

Maintain a living document of where you are right now in a project.

Activation

When this skill activates, output:

📍 State: Updating project state...

Then execute the protocol below.

Context Guard

ContextStatusPriority
User says "update state", "save state", "project state"ACTIVE: update STATE.mdP1
User says "where was I", "where did I leave off"ACTIVE, read and present STATE.mdP1
User starts a session and STATE.md existsACTIVE, read silently, use as contextP2
User says "save diary" or "log session"DORMANT, Diary handles full session logsnone
User says "save project" or "handoff"DORMANT, Project skill handles lifecyclenone
User asks to recall past sessionsDORMANT, Echo handles historical recallnone

Protocol

Reading State (session start or "where was I")

  1. Check for STATE.md in the current project's .claude/ directory:
    {project_dir}/.claude/STATE.md
  2. If found, read it and present a brief summary:
    • What was being worked on
    • Any blockers
    • The immediate next step
  3. If not found, say: "No STATE.md exists yet. I can create one after we start working."

Writing/Updating State

  1. Gather current state:
    • What task/phase is actively being worked on right now
    • Decisions made during this session (with rationale)
    • Open blockers or unanswered questions
    • Explicit next steps (not vague, specific enough to resume cold)
    • Key files modified recently
  2. Check git status for uncommitted work:
    git status --short
  3. Write STATE.md to the project's .claude/ directory:
    # Project State
    *Last updated: {YYYY-MM-DD HH:MM}*
    
    ## Currently Working On
    {Active task or phase: be specific}
    
    ## Decisions Made
    - {Decision}: {Rationale}
    
    ## Blockers
    - [ ] {Blocker description}
    
    ## Next Steps
    1. {Immediate next action, specific enough to start cold}
    2. {Following action}
    
    ## Recently Modified Files
    - {file path}: {what changed}
    
    ## Uncommitted Changes
    {List any unstaged/uncommitted work, or "None: clean working tree"}
  4. Confirm with a brief summary of what was saved.

Deconfliction

SkillWhat it tracksWhen
StateCurrent snapshot, where you are right nowDuring session, living document
DiaryHistorical log, what you did in a sessionEnd of session, append-only
ProjectProject lifecycle, handoff between sessionsSession boundaries
WorkTask list, what needs to be doneWhen planning/tracking todos

State is the present tense complement to Diary's past tense. State tells you where to resume; Diary tells you what happened.

Inputs

  • Current working context (project, files, git status)
  • User's description of current state (or auto-detected from session)

Outputs

  • {project_dir}/.claude/STATE.md: updated living document
  • Brief confirmation summary

Example Usage

User: "update state"

📍 State: Updating project state...

Saved: C:\Projects\AdminStack\.claude\STATE.md

Currently: Building CC Monitor notification system
Blockers: None
Next: Wire up WebSocket events to notification dropdown

This will auto-load next session for seamless pickup.

Level History

  • Lv.1: Base: Living STATE.md creation and update protocol. Read via Work Step 0 or manual invocation. Deconfliction with Diary/Project/Work. (Origin: MemStack v3.1, Feb 2026)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.