agent-bus-workflows

agent-bus-workflows is a skill for Claude Code, Codex from MustaphaSteph/agent-bus-plugins. It costs 40 tokens per session (337 once invoked), scanned A, original, MIT.

A workflow guide for running an agent-bus software team with a backlog, Kanban board, shared memory, ownership rules, testing, and review gates. A Kanban board tracks work as it moves through stages such as to do, active, review, and done.

In plain words
What is it for?
Use it to organize agent-bus tasks, assign edit scopes, record durable handoffs, require verification, and produce a final merge report.
Why use it?
It gives multiple coding agents a shared process for claiming work, recording decisions, checking results, and avoiding conflicting edits.

Skill for Claude CodeCodex

Part of the agent-bus plugin — 5 skills, 1 MCP server, 1 plugin shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/mustaphasteph/agent-bus-plugins/agent-bus-workflows
Any agent
npx skills add MustaphaSteph/agent-bus-plugins --skill agent-bus-workflows
Clone the repo
git clone --depth 1 https://github.com/MustaphaSteph/agent-bus-plugins

Made for: Claude Code, Codex.

Or install agent-bus, the plugin that ships this one along with the rest of its 5 skills, 1 MCP server, 1 plugin.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-bus-workflows

README.md
[![agentmods](https://agentmods.dev/badge/skills/mustaphasteph/agent-bus-plugins/agent-bus-workflows.svg)](https://agentmods.dev/skills/mustaphasteph/agent-bus-plugins/agent-bus-workflows)
Your own site
<a href="https://agentmods.dev/skills/mustaphasteph/agent-bus-plugins/agent-bus-workflows"><img src="https://agentmods.dev/badge/skills/mustaphasteph/agent-bus-plugins/agent-bus-workflows.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00337
Opus 5 $0.00020 $0.00169
Sonnet 5 $0.00008 $0.00067
Haiku 4.5 $0.00004 $0.00034

Measured 4d ago against content hash 36d90d393a69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-bus-workflows scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/agent-bus-workflows/SKILL.md · 62 lines

What it actually says

agent-bus workflows

Use this when the user wants agent-bus to behave like a software team, not just a mailbox.

Backlog and Kanban

Capture ideas as backlog tasks. Promote only when the team is ready.

Typical flow:

backlog -> todo/open -> accepted/claimed -> doing/working
-> testing -> review -> done/completed

The CLI board:

agent-bus backlog --team <team>
agent-bus kanban --team <team> --watch
agent-bus done --team <team>

Loop memory pattern

Agents should write durable memory for:

  • decisions
  • current risks
  • done work
  • next actions
  • handoff notes

Pin only durable handoffs/risks/facts that should survive session compaction or tomorrow's restart.

Verifier gate

For implementation tasks, "done" requires:

  • implementation done
  • test evidence recorded
  • reviewer/verifier approved if required
  • final report says safe

Use independent review when the implementer should not self-approve.

Conflict protection

Assign edit scopes before editing. Broad review/read scopes should not create edit conflicts. If two agents need the same file, one owns the edit task and the other reviews.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 62 lines · 0 tokens per session scan A 36d90d393a69

Subscribe to this mod's changes

agent-bus-workflows is a skill published in the GitHub repository MustaphaSteph/agent-bus-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 337 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

decision-map

Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…

SethGammon/Citadel · 77 tokens

merge-review

Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.

SethGammon/Citadel · 40 tokens

unharness

Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.

SethGammon/Citadel · 59 tokens

retro

Close an initiative by learning from it - spawns the retrospective agent over the ledger, the notes and the agents' reports, records what changed and what was rejected, and writes durable repo facts into .tyran/knowledge/. Runs at the end of an initiative; also available as /tyran:retro.

jjanczur/tyran · 62 tokens

status

Where is the work right now. Regenerates the projections and the kanban board from the journal and answers with the progress line, the agents still running, the open gates and the resume steps. Read-only. Use for /tyran:status or when asked what is going on.

jjanczur/tyran · 58 tokens

heartbeat

This skill should be used when the user asks to "run a heartbeat", "run the agent loop", "process GitHub issues", "check for work", or runs the /heartbeat command. Executes the WoterClip heartbeat — picks up GitHub issues, resolves personas, does work, and reports back.

wotai-dev/woterclip · 64 tokens