agentleFS
Sign inStart free
mayozmayoz/rabbit/skills/reload/SKILL.md

reload

Skill1 starsChanged 8 days agoMITView on GitHub

Read the workflow file again in a running Rabbit task or dev session, so later steps follow its current instructions. Reports read errors and what changed, and runs no other step. Use when the user says reload, reload the workflow, or read the workflow again.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. paulCalvert/claude-code-skills★ 1same name

    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 repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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:

    Profile: Read ~/.config/rabbit/profile.md.

    line 12
  2. Very specific:

    No Rabbit session: leave out "The next step follows it." and say there is no WF to use here.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Reload

Reads the workflow file again and replaces this session's WF. Nothing else happens: no stage starts, moves on or runs again, no tracker write, no message to another session, no question, no repository change.

  1. Profile. Read ~/.config/rabbit/profile.md. Missing or unreadable: send setup.needed with {{missing}} = the profile, and stop. Use only its Chat language (LANG, as the session already uses it), Workspace and Workflow: lines; other values keep what this session already uses.
  2. Session. A dev session has a Dev: line whose worktree is this folder in <Workspace>/*/*/jira.md. A task session's folder is <Workspace>/<sprint>/<KEY> (its name a task key). Neither: this is no Rabbit session.
  3. Read. No Workflow: line: WF is empty, {{changes}} = "no workflow file in the profile"; go to step 5. Otherwise run PY -I "${CLAUDE_PLUGIN_ROOT}/skills/task/scripts/workflow.py" <path> (PY: ${CLAUDE_PLUGIN_ROOT}/skills/task/references/rules.md).
    • Exit 3: send error.workflow-missing and stop. The old WF is not used again: the session waits for a fixed file and another /rabbit:reload.
    • Its JSON is the new WF. WF.unknown not empty: send note.unknown-heading.
  4. Changes. Compare with the WF this session read before: the stages whose instructions were added, removed or changed, by heading (Environment, Push:After). Nothing changed: "no changes". No earlier WF in this session (after a compaction): "loaded" and the stage headings. In a dev session only Environment, Execute and Push (in) count.
  5. Report. Send done.reload. {{placeholders}}: the ones in WF.placeholders that have no Answer: line in jira.md; empty when none. No Rabbit session: leave out "The next step follows it." and say there is no WF to use here.

From the next step on, apply the new WF exactly as the session's own skill says: a task session takes every stage, a dev session Environment, Execute (before, in, after) and Push.in. A question still waiting (Asked:) stays open as it is.

Messages come from ${CLAUDE_PLUGIN_ROOT}/skills/task/references/messages.md by id, sent in LANG.

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.

Check your setup, free