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/antimetal/cursor-plugin/fixnpx skills add antimetal/cursor-plugin --skill fixgit clone --depth 1 https://github.com/antimetal/cursor-pluginWhat 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 | $0.00081 | $0.00687 |
| Opus 5 | $0.00041 | $0.00344 |
| Sonnet 5 | $0.00016 | $0.00137 |
| Haiku 4.5 | $0.00008 | $0.00069 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix
You are applying Antimetal's remediation to the user's actual codebase. The remediation comes from Antimetal's view of the infrastructure -- your job is to bridge the gap between that and the local code.
Get the Plan
Use get_issue_fixes with the issue ID. Returns remediation groups organized into three categories:
Fix Categories
Immediate Fix—Fast stabilization when something is actively broken. Stops the bleeding but may not address the underlying cause.
Comprehensive Fix—The proper, complete solution. Addresses root cause with well-engineered changes.
Preventative Fix—Monitoring, alerts, and safeguards that prevent recurrence. Nice-to-have, not urgent.
Which to apply
Default: Comprehensive Fix. This is the right answer most of the time -- it solves the problem properly.
Exception: Immediate Fix first when the issue is ongoing and having business impact (service down, users affected, errors spiking). Stabilize first, then circle back to the comprehensive fix once the fire is out.
Bonus: Preventative Fix -- offer this after the main fix is applied. Frame it as "while we're here, want to add monitoring so we catch this earlier next time?" Don't apply it automatically.
Step Types
Each fix category contains steps, each with a type:
- info: Context for why the fix works. Present this so the user understands the reasoning before you change anything.
- code: File changes as
{ filename, language?, content }. These need adaptation (see below). - cli: Shell commands to execute. These need adaptation (see below).
Adapt, Don't Paste
Antimetal generates remediation from its infrastructure-level view. File names, paths, and patterns may not match the local codebase exactly. This is the critical skill:
Code Steps
- Find the actual files -- the filenames in remediation are Antimetal's best guess. Search the local codebase for the real targets (Glob for filenames, Grep for relevant code patterns).
- Read context -- understand the surrounding code before applying changes. The fix should integrate naturally, not look bolted on.
- Apply intelligently -- use the remediation as intent, not as a literal diff. If the local code uses different variable names, patterns, or structure, adapt the fix to match.
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.
- 2d ago First seen · 61 lines · 81 tokens per session scan A 4c04b02ae057
fix is a skill published in the GitHub repository antimetal/cursor-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 687 once invoked, about $0.0004 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
Incident Response Planner
Analyze an infrastructure incident alert and produce a structured response plan plus an executable on-call runbook. Use for incident, alert, on-call, and runbook requests.
setup-environment-profile
Point the ilert CLI at a staging, preview or self-hosted ilert environment by giving it its own profile.
ilert-essentials
Core ilert concepts and CLI behaviour: the object model and the rules behind the field names.
migrate-from-opsgenie
Map Opsgenie resources onto ilert equivalents.
migrate-from-pagerduty
Map PagerDuty resources onto ilert equivalents.
migrate-from-statuspageio
Map Statuspageio (Atlassian Statuspage) resources onto ilert status page equivalents.