agentleFS
gregmosgregmos/memoforge/skills/status/SKILL.md

status

Skill38 starsChanged 48 days agoMITView on GitHub

Read-only status of memoforge tasks — list every task, or report the phase, progress and event timeline of one task_id. Never mutates state. Use only when explicitly invoked via /memoforge:status.

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

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 146 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the task is unfinished, the one-line hint: Resume with /memoforge:continue <task_id>.

    line 44
  2. Very specific:

    Call Read on the files you cite (state.json, the deliverable, summary.md) so the host shows the user a clickable card.

    line 46

“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

memoforge / status — read-only

This skill only reads. Never write state.json, never run mf next, mf report, mf gate parse, mf task new, mf task cancel or any other command that changes a task, and never dispatch a subagent. To act on a task, tell the user to run /memoforge:continue [task_id].

Every reply to the user is in the task's ui_language (D-178): the report lines below are written in the language the task's ui_language names (read it with mf state get --workdir W --path ui_language; path_not_found: ui_language is a task from before the option, which means English — a business answer, never a CLI failure). Never translate the text_fallback reply forms the CLI prints — pass those verbatim.

mf = ${CLAUDE_PLUGIN_ROOT}/scripts/mf (use mf.cmd if that one is not executable in this host).

No argument — list every task

mf task list --human

The same command without --human returns {"tasks": [{task_id, current_phase, mode, created_at, work_dir, terminal, gate, cancel_requested, schema_version}], "count": N}. Print a compact table of those fields, newest first, and mark schema_version < 2 rows as v1 (not resumable). If count is 0, print No memoforge tasks found. Start one with /memoforge:memo "<question>". and END.

With a task_id — one task

Resolve the work dir first: mf task list and match task_id (its row carries work_dir). If nothing matches, print task_id `<arg>` not found and END. Then, with W = that work_dir:

mf state get --workdir W --path progress        # phase, position/total, active step, last chat line
mf state get --workdir W --path current_phase
mf state get --workdir W --path final_status
mf events analyze --workdir W --human           # timeline, serial dispatch, silent gaps

mf state get --workdir W without --path prints the whole state; prefer narrow --path reads (config, attempts, draft_versions, published, steps) over dumping everything. Field meanings: docs/state.md.

Report, in plain text:

  1. task_id, phase, mode, created, and final_status when the task is terminal.
  2. Progress: position/total, the last chat_line, and the open step if there is one.
  3. Draft versions and the deliverable path (final_docx_path), plus deliverable.md / summary.md under the work dir when present.
  4. The headline findings of events analyze (serial dispatch, silent gaps, hooks_absent).
  5. If the task is unfinished, the one-line hint: Resume with /memoforge:continue <task_id>.

Call Read on the files you cite (state.json, the deliverable, summary.md) so the host shows the user a clickable card; print the paths as plain text, not as markdown links. END the turn.

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.