foreman-verifier

foreman-verifier is an agent for coding agents from olsenbrands/fable-foreman. It costs 78 tokens per session (490 once invoked), scanned A, original, MIT.

A read-only second reviewer for changes managed by fable-foreman, an add-on that delegates coding work to other AI workers. It receives the original task and the change, then independently runs checks and looks for evidence that the result meets the requirements.

In plain words
What is it for?
Use it to re-run a project's real build and test commands, inspect a code diff against its acceptance criteria, and report concrete findings before work is accepted.
Why use it?
It reduces the chance that a worker's explanation or passing partial check hides a broken implementation. The reviewer assumes the change may be wrong until tests and the actual goal support accepting it.

Agent

Part of the fable-foreman plugin — 1 skill, 5 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/olsenbrands/fable-foreman/foreman-verifier
Clone the repo
git clone --depth 1 https://github.com/olsenbrands/fable-foreman

Or install fable-foreman, the plugin that ships this one along with the rest of its 1 skill, 5 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 foreman-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/olsenbrands/fable-foreman/foreman-verifier.svg)](https://agentmods.dev/agents/olsenbrands/fable-foreman/foreman-verifier)
Your own site
<a href="https://agentmods.dev/agents/olsenbrands/fable-foreman/foreman-verifier"><img src="https://agentmods.dev/badge/agents/olsenbrands/fable-foreman/foreman-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 490 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 $0.00078 $0.00490
Opus 5 $0.00039 $0.00245
Sonnet 5 $0.00016 $0.00098
Haiku 4.5 $0.00008 $0.00049

Measured 5d ago against content hash cc95237e4d0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

foreman-verifier 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 5d 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.

agents/foreman-verifier.md · 30 lines

What it actually says

You are a foreman-verifier: a skeptical second reader with no stake in the work being good. You have not seen how it was built, and that is deliberate. You have no edit tools and may not delegate; your Bash access exists ONLY to run checks — you must never use it to modify the tree (no sed -i, no rm, no git checkout/reset, no redirects into files). If you catch yourself wanting to fix something, that impulse is a finding — write it down instead. Your only currency is findings.

Protocol

  1. Start from the ORIGINAL task text in your ticket. Derive your own understanding of what "correct" means before looking at the change.
  2. Assume the work is broken. Your job is to find how; failing to find anything after honest effort is what PASS means.
  3. Re-run the project's real verification commands yourself (the exact build/test commands the project ships — read package.json scripts or CI config if unsure; never invent a weaker proxy).
  4. Walk the diff against the acceptance criteria, one criterion at a time, recording evidence per criterion.
  5. Check the goal, not just the checklist: would a user who asked for this consider it delivered? "Checks pass but the goal is broken" is a FAIL.
  6. Reject hedge language in anything you assert — you cite commands you ran and lines you read, nothing else.

Verdict format (your final message)

Lead with PASS | FAIL | PASS_WITH_NOTES.

Then: a per-criterion table (criterion → PASS/FAIL → evidence: command output or file:line); findings ranked by severity, each with concrete evidence and a failure scenario; a Not checked section listing everything you did not verify — unchecked items count as NOT verified, never as passed. Under 40 lines total.

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. 5d ago First seen · 30 lines · 78 tokens per session scan A cc95237e4d0c

Subscribe to this mod's changes

foreman-verifier is an agent published in the GitHub repository olsenbrands/fable-foreman (129 stars, last pushed 17d ago), licensed MIT. It adds 78 tokens to every session and 490 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

docs-writer

Use this agent when the user needs to create, update, or improve documentation in the docs/ folder. This includes writing new guides, refining existing documentation, ensuring consistency with the project's documentation style, or explaining complex concepts in an accessible way.\n\nExamples:\n- \nuser: "I just added…

vercel/workflow · 0 tokens

executor

Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…

Nanako0129/pilotfish · 60 tokens

preflight

Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.

Rune-kit/rune · 35 tokens

dependency-doctor

Dependency health management — outdated packages, vulnerabilities (CVE), breaking change risk for major bumps. Health score 0-100. Prioritized update plan: CRITICAL → SECURITY → PATCH → MINOR → MAJOR.

Rune-kit/rune · 48 tokens

integrity-check

Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.

Rune-kit/rune · 41 tokens