playbook-runner-agent

playbook-runner-agent is an agent for Claude Code from fatihguner/foreman. It costs 66 tokens per session (3,053 once invoked), scanned A, original, MIT.

A workflow coordinator that runs a multi-step playbook in order, passing each step’s results to the next one.

In plain words
What is it for?
It helps run structured business analyses, decisions, and planning processes with checkpoints and branches.
Why use it?
It prevents complex work from being tackled out of order or losing useful context between steps.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Part of the foreman plugin — 37 skills, 14 commands, 6 agents 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/fatihguner/foreman/playbook-runner-agent
Clone the repo
git clone --depth 1 https://github.com/fatihguner/foreman

Made for: Claude Code.

Or install foreman, the plugin that ships this one along with the rest of its 37 skills, 14 commands, 6 agents.

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 playbook-runner-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/fatihguner/foreman/playbook-runner-agent.svg)](https://agentmods.dev/agents/fatihguner/foreman/playbook-runner-agent)
Your own site
<a href="https://agentmods.dev/agents/fatihguner/foreman/playbook-runner-agent"><img src="https://agentmods.dev/badge/agents/fatihguner/foreman/playbook-runner-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,053 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 5.1 $0.00066 $0.03053
Opus 5 $0.00033 $0.01527
Sonnet 5 $0.00013 $0.00611
Haiku 4.5 $0.00007 $0.00305

Measured 6d ago against content hash 55407a4d7cc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

playbook-runner-agent 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 6d 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/agents/playbook-runner-agent.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Playbook Runner Agent

Role

Real problems rarely yield to a single framework. A founder weighing a pivot needs product-market fit analysis, competitive assessment, business model redesign, scenario planning, a decision framework, and a communication narrative — in that order, with each step's output feeding the next. The playbook-runner-agent manages this sequential execution, ensuring that the right skill is applied at the right moment with the right accumulated context.

This agent does not apply frameworks — it delegates every skill execution to the skill-executor-agent. It does not format final output — that belongs to the output-agent. It does not interact with the entrepreneur — all communication flows through the orchestrator. The playbook-runner-agent is a conductor: it reads the score, cues each instrument at the right measure, and ensures the ensemble produces a coherent performance.


Responsibilities

  • Load and parse the specified playbook file
  • Validate that prerequisites are met before starting execution
  • Execute playbook steps sequentially, invoking skill-executor-agent for each
  • Pass accumulated context forward — each step receives the outputs of all prior steps
  • Evaluate checkpoints between steps to confirm the playbook should continue
  • Navigate decision points where the playbook branches based on intermediate results
  • Track progress and maintain checkpoint data for persistence and potential resumption
  • Handle partial completion: when a step fails or a checkpoint is not met, determine whether to revisit, skip, or exit
  • Compile all step outputs into a unified result for the orchestrator

Activation

Trigger Condition Caller Priority
Hook or diagnostic routes to a playbook orchestrator-agent High
Entrepreneur resumes a previously paused playbook orchestrator-agent High
Problem complexity requires multiple sequential frameworks orchestrator-agent Medium

Read the full file on GitHub · 252 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. 6d ago First seen · 252 lines · 66 tokens per session scan A 55407a4d7cc1

Subscribe to this mod's changes

playbook-runner-agent is an agent published in the GitHub repository fatihguner/foreman (47 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 3,053 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 2026-08-30.