agentleFS
Sign inStart free
ruverdruverd/bulma/skills/bulma-bus/SKILL.md

bulma-bus

Skill1 starsChanged 50 days agoMITView on GitHub

Shared bus for the bulma agent graphs (developer, qa, triage, reviewer, lstm). Use when switching graphs, writing or reading a .bulma-bus envelope, or resuming a stacked handoff between those agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Read .bulma-bus/STACK.md (last line = active graph).

    line 48

≈ “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

Bulma bus

Five graphs, one session. They do not nest.

developer ⇄ qa ⇄ triage
     ⇄ reviewer
     ⇄ lstm

Communication = files under .bulma-bus/ in the global home (DISK.md) — never the git root. Protocol: PROTOCOL.md. Jobs / QA queue: JOBS.md.

Who orchestrates

The main thread is the only graph runner.

SituationAction
Main, outbound edgeWrite envelope → push stack → load the target graph SKILL/GRAPH and continue
Already a subagentWrite envelope, return. Do not spawn a graph
Resume / /bulma-busRead STACK.md + latest envelope → load that graph

Never spawn_worker with type bulma_qa / bulma_triage / bulma_developer / bulma_reviewer / bulma_lstm. Those names are graphs (main-thread roles). Overflow developer/reviewer/lstm work = one general-purpose worker + worktree (JOBS.md, bulma-host). Never a second QA worker.

Resume

/bulma-bus resume
  1. Read .bulma-bus/STACK.md (last line = active graph).
  2. Read .bulma-bus/ENVELOPE.md.
  3. load_graph the last STACK line (bulma-<name> SKILL.md + GRAPH.md).
  4. Continue from that graph's STATE. Do not restart.
  5. Also print JOBS.md: qa_active with its qa_claimed_at age, qa_waiting, worker rows. Flag a claim past qa_lease_minutes — that is a crashed QA, not a busy one.

Chat

Short, chat language (bulma-memory): S: bus <from>→<to> <type> · P: active graph · qa_active / queue.

Timing, laps, and host token totals: LEDGER.md. bulma report reads them. Human-review observations for lookbacks: INSIGHTS.md.

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