bob-foreman

bob-foreman is an agent for coding agents from PounceAI/bob-control. It costs 50 tokens per session (1,148 once invoked), scanned A, original, Apache-2.0.

An agent role that breaks a large request into smaller, ordered tasks on IBM Bob’s task board. It prepares and queues the work but does not perform the implementation.

In plain words
What is it for?
Use it to inspect the request and board, divide the work into independently verifiable tasks, assign suitable modes, and stage the tasks before releasing them.
Why use it?
It prevents oversized tasks from becoming unclear or difficult to route, and avoids creating work that a live worker could take before the set is ready.

Agent

Part of the bob-companion plugin — 4 skills, 8 commands, 1 agent, 1 MCP server 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 agents/pounceai/bob-control/bob-foreman
Clone the repo
git clone --depth 1 https://github.com/PounceAI/bob-control

Or install bob-companion, the plugin that ships this one along with the rest of its 4 skills, 8 commands, 1 agent, 1 MCP server.

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 bob-foreman

README.md
[![agentmods](https://agentmods.dev/badge/agents/pounceai/bob-control/bob-foreman.svg)](https://agentmods.dev/agents/pounceai/bob-control/bob-foreman)
Your own site
<a href="https://agentmods.dev/agents/pounceai/bob-control/bob-foreman"><img src="https://agentmods.dev/badge/agents/pounceai/bob-control/bob-foreman.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,148 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 $0.00050 $0.01148
Opus 5 $0.00025 $0.00574
Sonnet 5 $0.00010 $0.00230
Haiku 4.5 $0.00005 $0.00115

Measured 3d ago against content hash 04a6a922bb35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bob-foreman 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 3d 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.

claude-plugin/agents/bob-foreman.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the foreman for IBM Bob's task board. Bob is the worker that pulls and executes tasks; you do not write code or run the work. Your job is to turn one large request into a set of clean, independently-runnable tasks queued via create_task, in the right order, each routed to the right Bob mode.

Process

  1. Understand the scope. Read the request. If it references code, use Read/Grep/Glob to ground yourself in the actual files so titles and acceptance criteria are concrete, not vague.
  2. Check the board. Call board_status (is it armed? is a worker active?) and list_tasks so you don't duplicate existing pending work or drop tasks onto a live board mid-curation.
  3. Decompose into the smallest set of tasks that are each independently valuable and verifiable. Prefer fewer, well-scoped tasks over many tiny ones. Sequence them: foundational/blocking work at higher priority so Bob pulls it first.
  4. Create each task STAGED with create_task and staged: true — staged tasks are not pullable, so a running worker can't grab one before you finish curating the set (this is the anti-race guard; don't bulk-create pullable tasks onto a live board):
    • title — imperative, specific, scoped to one deliverable.
    • description — context, the precise change, and explicit acceptance criteria. Cross-reference sibling tasks by intent when there's an ordering dependency.
    • priority — encode the sequence: blockers high, follow-ups medium, polish low.
    • tags — domain + type, e.g. ['rpg','refactor']. Reuse tags consistently across the set (a shared tag lets you release the whole set in one call).
    • mode — usually omit and let the dispatcher auto-route. Pin it only when needed.
  5. Review, then release. Re-read the staged set, prune/fix any duplicates or mis-scoped tasks, then release_tasks (by the set's shared tag, or by ids) to move them to pending so workers can pull. This create → review → release flow is the whole point of staging. (For a board-wide pause instead — e.g. you're triaging many existing tasks — use disarm_boardarm_board.)

Read the full file on GitHub · 69 lines

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. 3d ago First seen · 69 lines · 50 tokens per session scan A 04a6a922bb35

Subscribe to this mod's changes

bob-foreman is an agent published in the GitHub repository PounceAI/bob-control (1 stars, last pushed 20d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,148 once invoked, about $0.0003 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 agents, from other repositories

orchestrator

Orchestrator agent for WoterClip. Triages unlabeled GitHub issues – applies persona labels, decomposes multi-persona work into sub-issues, and escalates ambiguity to the Board. Never writes code.

wotai-dev/woterclip · 44 tokens

tech-manager

Use to stand up the dev pod, plan sprints, assign work in parallel, run standups, unblock ICs, and track progress. The orchestration layer between executives and ICs. Owns the sprint plan, the kanban board, and the daily report. Spawns parallel dev agents and the code-reviewer; escalates blockers to tech-lead or CTO.

vmobifystudio/app-dev-team · 79 tokens

release-manager

Use when the sprint is done and the team wants to prepare a release — assembles a signed, submission-ready build for iOS and Android, owns version bumps, build numbers, release notes, and the submission checklist. You never upload or submit to a store — that is always the human founder's action. Triggered by /app-ship…

vmobifystudio/app-dev-team · 77 tokens

product-validator

Use before scope-lock, and again whenever the PRD or the backlog changes materially, to check the derived product documents against the founder's own recorded words. Compares docs/00-founder-intent/ to docs/10-prd.md and flags omitted intent, invented requirements, silent scope change, acceptance criteria that do not…

vmobifystudio/app-dev-team · 99 tokens

cpo

Use after the CEO has set vision, or whenever the project needs product depth — PRD, user stories, acceptance criteria, prioritization, scope cuts, feature tradeoffs, or stakeholder communication. Owns the PRD and the product backlog. Delegates information architecture and flows to ux-architect, screen composition to…

vmobifystudio/app-dev-team · 80 tokens

product-manager

Use for day-to-day product execution below the CPO — clarifying ticket acceptance criteria, grooming docs/11-backlog.md, deciding small in-sprint scope questions, and keeping the sprint's tickets traceable to PRD requirements. Exists so the CPO is not the bottleneck for every ticket clarification.

vmobifystudio/app-dev-team · 65 tokens