FM-Agent-Diagnose

FM-Agent-Diagnose is a skill for Claude Code from fmagent-project/FM-Agent-Plugin. It costs 41 tokens per session (1,310 once invoked), scanned A, original, Apache-2.0.

A results viewer for FM-Agent, which reads the tool's saved output and presents its detected bugs and verification details.

In plain words
What is it for?
Use it to view summaries, browse bug reports page by page, and inspect individual bug details in the project's fm_agent directory.
Why use it?
It lets you inspect completed analysis results without rerunning the analysis, and clearly reports when no completed output exists.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the fm-agent-plugin plugin — 9 skills 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 skills/fmagent-project/fm-agent-plugin/diagnose
Any agent
npx skills add fmagent-project/FM-Agent-Plugin --skill diagnose
Clone the repo
git clone --depth 1 https://github.com/fmagent-project/FM-Agent-Plugin

Made for: Claude Code.

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

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 FM-Agent-Diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmagent-project/fm-agent-plugin/diagnose.svg)](https://agentmods.dev/skills/fmagent-project/fm-agent-plugin/diagnose)
Your own site
<a href="https://agentmods.dev/skills/fmagent-project/fm-agent-plugin/diagnose"><img src="https://agentmods.dev/badge/skills/fmagent-project/fm-agent-plugin/diagnose.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,310 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 $0.00041 $0.01310
Opus 5 $0.00020 $0.00655
Sonnet 5 $0.00008 $0.00262
Haiku 4.5 $0.00004 $0.00131

Measured 6d ago against content hash c8a4866091bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

FM-Agent-Diagnose 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.

plugins/fm-agent-plugin/skills/diagnose/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose and analyze FM-Agent output in the project directory.

Overview

This skill reads FM-Agent output (./fm_agent/) from the project directory. It presents a summary, lists bugs with pagination, and shows detailed bug reports on request. The primary data source is fm_agent/bug_validation/summary.json, with per-bug detail in corresponding .md and .result.json files.

Prerequisites

  • ./fm_agent/ directory must exist.
  • If files or directories are missing, FM-Agent analysis has not completed. DO NOT sleep and retry — finish diagnosis immediately with whatever is available.

Output Directory Structure

fm_agent/
├── phases.json                 # Analysis phase definitions and module groupings
├── fm_agent_file_list.json     # All source files processed
├── extracted_functions/        # Per-function extracted source snippets
├── spec_prompts/               # Generated spec prompts and topdown layer JSONs
├── logic_verification_results/ # Formal verification output
├── bug_validation/             # Bug reports (the directory you care about)
│   ├── summary.json            # Aggregated results — always start here
│   ├── <bug_id>.md             # Human-readable bug detail report
│   ├── <bug_id>.result.json    # Machine-readable bug summary (same fields as summary entry)
│   └── _probe_<bug_id>.*       # Compiled probe binary and code source

The <bug_id> uses -- as path separators, e.g. src--observer--net--server-cpp--accept.

Step 1: Report Summary

Always start here. Read fm_agent/bug_validation/summary.json.

The JSON contains these top-level fields:

  • total_reported — total bugs found
  • total_confirmed — bugs validated by probe
  • total_not_confirmed — bugs where probe did not reproduce the issue
  • total_error — bugs where probe execution failed
  • bugs — array of bug objects (see Step 2)

Present the summary as:

FM-Agent Analysis Summary

Total Reported: X
  Confirmed:     Y
  Not Confirmed: Z
  Errors:        W

Bug reports: fm_agent/bug_validation/

Read the full file on GitHub · 137 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 · 137 lines · 41 tokens per session scan A c8a4866091bb

Subscribe to this mod's changes

FM-Agent-Diagnose 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 41 tokens to every session and 1,310 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

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

Orchestrates Volcengine Cloud Detect (云拨测) false-alarm reduction for failing periodic-task dial points. Use for scheduled task scans, retrying failed nodes, control-testing node health, distinguishing real target outages from broken dial points, and suggesting same-type LastMile/IDC/Private replacement nodes. Runs the…

bytedance/agentkit-samples · 101 tokens