agentleFS
ffrolivaffroliva/gflow-cli/skills/status/SKILL.md

status

Skill367 starsChanged 58 days agoMITView on GitHub

Surfaces the current state of work in gflow-cli. Three variants at different levels of detail: full state (status), next task only (next), active plan identity (active). All variants run scripts/dev/active_plan.py and filter its output to the requested detail level.

177 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use off, list and 10 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.
  • StakeholderSenseiSkill

    off

    Disable polygraph for this repo (user-only escape hatch; all hooks no-op)

    Also in 4 projects that use this

  • SuShuhengSkill

    list

    Use when checking obshare-cli upload history, finding document tokens, or reviewing previous upload URLs and permission snapshots.

    Also in 8 projects that use this

  • kennethleungtySkill

    pause

    Pause — stop the music (alias for /stop)

    Also in 6 projects that use this

  • codebycoreySkill

    new

    Start a new change with a proposal. Use when starting a feature, creating a proposal, or beginning planned work.

    Also in 7 projects that use this

  • michaelenglandSkill

    import

    This skill should be used when the user wants to import an existing .pptx file into deckwright, bring in a PowerPoint that was created outside this tool, reverse-engineer a presentation for editing, or invoke /deckwright:import. Converts a .pptx into a PptxGenJS generation script so it can be edited and regenerated through the deckwright pipeline.

    Also in 5 projects that use this

  • genomewalkerSkill

    resume

    Resume a thread by loading its ~800-token context capsule

    Also in 15 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 5 are distinctive, and 8 are very specific to this project.

  • 0

    Common

    Most of the 146 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After completing a task: "what comes next?"

    line 37
  2. Distinctive:

    Before adding scope: "does this belong to the current plan?"

    line 38
  3. Very specific:

    Return: only the content from --- Next task --- onward.

    line 48
  4. Very specific:

    If no --- Next task --- separator is present (root PLAN.md mode), return the full script output — the phase block is already task-level …

    line 51
  5. Distinctive:

    If the script output contains "All steps complete", say so and suggest:

    line 54
  6. Distinctive:

    Return: only the header lines — Plan path, Title, Goal, Progress count.

    line 70
  7. Very specific:

    If the output contains --- Next task ---, stop before that separator.

    line 71
  8. Very specific:

    If no separator is present (root PLAN.md mode — _summarise_root_plan() output), return the full output.

    line 72
  9. Very specific:

    Before /gflow:predict or /gflow:scenario: confirm the proposal fits the active scope

    line 75
  10. Distinctive:

    When context is long and you need a one-line anchor without task block noise

    line 77
  11. Very specific:

    If the caller passed a slug (e.g.

    line 89
  12. Very specific:

    If neither, run the script without --feature (falls back to root PLAN.md).

    line 91
  13. Very specific:

    Antigravity (agy): read this file before asking "what's the next task?".

    line 99

“Common” is measured: kept by at least 6 in 10 of the 146 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

status — Plan State Reader

Three variants for different contexts. All backed by scripts/dev/active_plan.py.


Variants

status [feature] — Full state

The full picture: which plan file is active, its goal, progress (X/N tasks complete), and the next unchecked task block.

Script invocation:

# With a feature name (from $ARGUMENTS or conversation context):
uv run python scripts/dev/active_plan.py --feature <slug>

# Without a feature name (uses root PLAN.md):
uv run python scripts/dev/active_plan.py

Return: the complete script output verbatim.

When to call:

  • Starting a session: "where did we leave off?"
  • After completing a task: "what comes next?"
  • Before adding scope: "does this belong to the current plan?"

next [feature] — Next task only

The single next unchecked task block. No header noise.

Script invocation: same as status.

Return: only the content from --- Next task --- onward. Drop the Plan / Title / Goal / Progress header lines entirely.

If no --- Next task --- separator is present (root PLAN.md mode), return the full script output — the phase block is already task-level content.

If the script output contains "All steps complete", say so and suggest:

  • /gflow:changelog to review unreleased changes
  • /gflow:release if the phase is fully done

When to call:

  • "What do I do right now?" — between tasks, no orientation needed
  • Resuming mid-session after a context switch

active — Plan identity only

Just which plan is active and its goal. No task detail.

Script invocation: same as status.

Return: only the header lines — Plan path, Title, Goal, Progress count.

  • If the output contains --- Next task ---, stop before that separator.
  • If no separator is present (root PLAN.md mode — _summarise_root_plan() output), return the full output; it contains only orientation-level content with no task block.

When to call:

  • Before /gflow:predict or /gflow:scenario: confirm the proposal fits the active scope
  • Quick check: "are we in a superpowers plan or the root PLAN.md?"
  • When context is long and you need a one-line anchor without task block noise

What the script returns (reference)

  • Superpowers plan active: file path · title · goal · progress (X/N steps complete) · next unchecked task block
  • No superpowers plan: the first incomplete phase from PLAN.md (scope, sequence, definition of done)
  • All complete: "All steps complete." — prompt user toward /gflow:changelog + /gflow:release

Feature slug resolution

  1. If the caller passed a slug (e.g. shell-multi-prompt), pass it as --feature <slug>.
  2. Otherwise check conversation context for a feature name mentioned this session.
  3. If neither, run the script without --feature (falls back to root PLAN.md).

Integration

  • Claude Code: invoke via /gflow:status, /gflow:next, or /gflow:active (thin wrappers around this skill).
  • Cursor / Aider / Codex: include this file in context; call the variant by name.
  • Antigravity (agy): read this file before asking "what's the next task?".

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.

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.