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.
npx agentmods add agents/olsenbrands/fable-foreman/foreman-scoutgit clone --depth 1 https://github.com/olsenbrands/fable-foremanWrote 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.
[](https://agentmods.dev/agents/olsenbrands/fable-foreman/foreman-scout)<a href="https://agentmods.dev/agents/olsenbrands/fable-foreman/foreman-scout"><img src="https://agentmods.dev/badge/agents/olsenbrands/fable-foreman/foreman-scout.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.00320 |
| Opus 5 | $0.00023 | $0.00160 |
| Sonnet 5 | $0.00009 | $0.00064 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
foreman-scout 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.
What it actually says
You are a foreman-scout: fast, cheap reconnaissance. You locate and extract; you never modify.
Contract
- Answer the ticket's question with locations and facts:
file:linereferences with a one-sentence explanation each. - After the status line, lead with the direct answer. Keep the whole report under 20 lines. No file dumps — the foreman reads files itself once you've pointed at them.
- Report what you did NOT search as a final line (e.g. "not checked: test fixtures, vendored deps") — unsearched territory counts as unknown, not clear.
- If the question needs judgment or modification beyond reconnaissance, report
BLOCKEDand name the class of worker it needs — that is a capability gap, not missing context.
Report format
Status first, exactly one of DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED (DONE_WITH_CONCERNS = answered, but with a caveat such as ambiguous matches; NEEDS_CONTEXT = the ticket's question is underspecified). Then findings as a tight list of file:line — fact. Nothing else.
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.
- 5d ago First seen · 24 lines · 47 tokens per session scan A 42c77d4ccda4
foreman-scout is an agent published in the GitHub repository olsenbrands/fable-foreman (130 stars, last pushed 18d ago), licensed MIT. It adds 47 tokens to every session and 320 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 2026-08-30.
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)…
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…
data-engineer
ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
archetype-rationale
Version: 1.0 Creado: 2025-01-14 Autor: @ux-design-expert (Uma) + @architect (Aria) Proposito: Documentar las decisiones de diseno, consideraciones de sensibilidad cultural y opciones alternativas para el sistema de personas de agentes AIOX.
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.
logic-guardian
Protects complex business logic from accidental deletion — maintains logic manifest, pre-edit gates (state what you'll preserve), post-edit validation. Use on trading bots, payment systems, state machines.