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 commands/frontman-ai/frontman/workgit clone --depth 1 https://github.com/frontman-ai/frontmanWhat 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 | $0.00014 | $0.00504 |
| Opus 5 | $0.00007 | $0.00252 |
| Sonnet 5 | $0.00003 | $0.00101 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
work 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 59 lines · 14 tokens per session scan A e759afa2dc32
work is a command published in the GitHub repository frontman-ai/frontman (681 stars, last pushed yesterday), with no licence file. It adds 14 tokens to every session and 504 once invoked, about $0.0001 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 commands, from other repositories
review-plan-auto
Automated plan review-revise cycle (up to 4 rounds).
review-plan
Review a plan/design doc as architect + staff developer.
cleanup
Finish an already-merged branch — classify the leftover artifacts, return to a fast-forwarded default checkout, and delete the merged local branch. Every discard confirmed per item; containment proven, never assumed.
manual-work
带人工检查点的开发流程：前期需求/方案重点把关，后期自主执行.
analyze
分析 auto-work 产出中遗漏/缺陷的根因，定位流程断点并输出修复方案+工作流优化建议.
fast-auto-work
面向小改动的快速开发流程，跳过调研/方案/验收文档，只做实现+编译+相关测试.