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 skills/fmagent-project/fm-agent-plugin/auto-fixnpx skills add fmagent-project/FM-Agent-Plugin --skill auto-fixgit clone --depth 1 https://github.com/fmagent-project/FM-Agent-PluginWrote 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/skills/fmagent-project/fm-agent-plugin/auto-fix)<a href="https://agentmods.dev/skills/fmagent-project/fm-agent-plugin/auto-fix"><img src="https://agentmods.dev/badge/skills/fmagent-project/fm-agent-plugin/auto-fix.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 | $0.00026 | $0.04653 |
| Opus 5 | $0.00013 | $0.02327 |
| Sonnet 5 | $0.00005 | $0.00931 |
| Haiku 4.5 | $0.00003 | $0.00465 |
Grade A, and why
FM-Agent-Auto-Fix 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.
How it starts
The opening of the file, as written. The whole thing — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the FM-Agent auto-fix orchestration loop for the current project.
Overview
This skill owns the verification-repair-review loop for FM-Agent. It enforces that only one auto-fix session is active in the repository, chooses full-project or incremental FM-Agent verification based on prior analysis state, collects bug artifacts from fm_agent/bug_validation/, dispatches one dedicated coding-agent sub-session per repair round, dispatches one dedicated reviewer sub-session after each repair round, and records machine-readable and human-readable session state under ./fm_agent_plugin/.
The reviewer agent's structured return envelope is the control signal for the loop after the initial FM-Agent verification. Do not infer the repair outcome from git diff or the coding agent's self-report.
All repair and review work happens inside the isolated git worktree snapshot that FM-Agent's --isolate run created during verification, never in the real project working tree. Only after the reviewer passes does the loop merge the snapshot's repairs back into the real current branch, auto-resolving any conflicts. The real working tree stays untouched until that final merge.
Argument: <intent-msg> (optional)
This skill takes one optional argument:
<intent-msg>: optional user-provided intent message describing what changed or what should be analyzed
If <intent-msg> is provided and the project uses incremental verification, pass it to fm-agent:run-incremental --incremental <intent-msg>.
Repair Round Limit
Before starting the loop, ask the user for the maximum number of coding-agent repair rounds allowed for this session.
Validate the answer before doing anything else:
- It must be a positive integer.
- If it is missing, zero, negative, or not an integer, ask the user for a positive integer before starting any session state changes.
- Record the validated value as
max_iterations.
Session Files
All session artifacts live under ./fm_agent_plugin/ in the current project directory. Generate a fresh session_id for each new run using the current timestamp, formatted as YYYYMMDD-HHMMSS.
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 · 476 lines · 26 tokens per session scan A 782aad3aade4
FM-Agent-Auto-Fix 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 26 tokens to every session and 4,653 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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.
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…