agentmods.dev

FM-Agent-Help

A help guide for the FM-Agent plugin, which uses language-model-based code reasoning to inspect codebases and detect bugs.

In plain words
What is it for?
Use it to learn how to install, configure, prepare, analyze, diagnose, automatically repair, export, or get help with FM-Agent.
Why use it?
It explains the plugin's commands and setup steps so you can choose the right operation and understand its requirements.

Skill for Claude CodeCodex

Part of the fm-agent-plugin plugin — 9 skills shipped together

2 1mo ago A scan 42 tokens original Apache-2.0
View the source file fmagent-project/FM-Agent-Plugin
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 skills/fmagent-project/fm-agent-plugin/help
Any agent
npx skills add fmagent-project/FM-Agent-Plugin --skill help
Clone the repo
git clone --depth 1 https://github.com/fmagent-project/FM-Agent-Plugin

Made for: Claude Code, Codex.

Or install fm-agent-plugin, the plugin that ships this one along with the rest of its 9 skills.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,911 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 $0.00042 $0.01911
Opus 5 $0.00021 $0.00955
Sonnet 5 $0.00008 $0.00382
Haiku 4.5 $0.00004 $0.00191

Measured 2d ago against content hash 70a9416cb6ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

FM-Agent-Help 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 2d 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.

plugins/fm-agent-plugin/skills/help/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Provide help and usage information for the FM-Agent plugin.

Overview

This plugin integrates FM-Agent into Claude Code or codex for automated code reasoning and bug detection. FM-Agent uses LLM-based Hoare-style verification to analyze codebases.

Available Commands

Command Description
/fm-agent:install Clone FM-Agent to the plugin data directory
/fm-agent:config Show/modify FM-Agent configuration
/fm-agent:preflight Check the environment is ready before running analysis
/fm-agent:run-full Execute full-project FM-Agent analysis on current project (background)
/fm-agent:run-incremental Execute incremental FM-Agent analysis on current project (background)
/fm-agent:diagnose View bug analysis results
/fm-agent:auto-fix Run verification-repair loop for the whole codebase
/fm-agent:export Export current conversation after a git commit
/fm-agent:help Show help information

install

Clone FM-Agent from official repository to the plugin data directory ($HOME/.fm-agent-plugin/FM-Agent/):

git clone https://github.com/fmagent-project/FM-Agent.git

Then run $HOME/.fm-agent-plugin/FM-Agent/install.sh to install dependencies.

config

Read and modify FM-Agent settings stored in $HOME/.fm-agent-plugin/FM-Agent/.env (loaded by FM-Agent via dotenv at runtime).

Workflow:

  • If .env does not exist, create it with default values
  • List the current .env values as a table
  • Ask whether to modify any settings; if yes, use AskUserQuestion (multi-select) to let the user pick which settings to modify and prompt for each new value
  • After writing changes, verify the selected backend. In local CLI backend mode, LLM_API_KEY is not required; in upstream OpenCode/API mode, verify LLM_API_KEY.

Configurable settings (all stored in .env):

  • LLM_API_KEY - API key (required only for upstream OpenCode/API mode)
  • LLM_API_BASE_URL - API endpoint (default: https://openrouter.ai/api/v1)
  • LLM_MODEL - Optional model passed to codex exec or claude -p; leave empty to use the selected CLI default
  • LLM_EFFORT - Optional reasoning effort passed to codex exec or claude -p; leave empty to omit the effort flag
  • FM_AGENT_MODEL_BACKEND - opencode, auto, codex-cli, or claude-cli (default: opencode)
  • OPENCODE_MODEL_PROVIDER - Model provider used by OpenCode (default: openrouter)

Read the full file on GitHub · 145 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. 2d ago First seen · 145 lines · 42 tokens per session scan A 70a9416cb6ed

Subscribe to this mod's changes

FM-Agent-Help is a skill published in the GitHub repository fmagent-project/FM-Agent-Plugin (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,911 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens