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/mnvsk97/eyeroll/fixgit clone --depth 1 https://github.com/mnvsk97/eyerollWrote 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/commands/mnvsk97/eyeroll/fix)<a href="https://agentmods.dev/commands/mnvsk97/eyeroll/fix"><img src="https://agentmods.dev/badge/commands/mnvsk97/eyeroll/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 | $0.00000 | $0.00531 |
| Opus 5 | $0.00000 | $0.00266 |
| Sonnet 5 | $0.00000 | $0.00106 |
| Haiku 4.5 | $0.00000 | $0.00053 |
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 3d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/eyeroll:fix
Watch a bug video, diagnose the issue, fix the code, and raise a PR -- all in one command.
Usage
/eyeroll:fix <url-or-path> [--context "..."]
What it does
/eyeroll:fix extends /eyeroll:watch with a full fix workflow:
- Analyze -- runs
eyeroll watchto produce a structured report - Diagnose -- extracts error messages, URLs, and search patterns from the report
- Search -- greps the codebase using suggested patterns and reads identified files
- Fix -- implements minimal, focused changes
- Test -- runs the project's test suite; writes a test if one would catch the bug
- PR -- creates a branch, commits, pushes, and opens a pull request
Examples
/eyeroll:fix https://loom.com/share/abc123
/eyeroll:fix ./bug.mp4 --context "checkout broken after PR #432"
/eyeroll:fix ./screenshot.png --context "this 500 error started yesterday"
Diagnosis flow
The agent extracts from the report:
- Exact error messages and status codes
- URLs and routes visible in the recording
- Search patterns from the Fix Directions section
- File references from codebase context
It then searches the codebase:
grep -r "TypeError: Cannot read properties" .
grep -r "stripe_id" .
If the context mentions a regression, it checks recent changes:
gh pr view 432
git log --since="1 week ago" -- src/checkout/
PR format
The generated PR includes:
## Summary
What was broken and why.
## Bug Evidence
- Video: <source URL>
- Error: <exact error message>
## Changes
- src/checkout/handler.py: Added null check for stripe_id
## Test Plan
- Verify checkout flow completes without error
Confidence gates
The agent adjusts its behavior based on diagnosis confidence:
| Confidence | Behavior |
|---|---|
| High | Implements fix, opens PR |
| Medium | Implements fix, opens PR as draft |
| Low | Presents findings, asks before implementing |
!!! warning "Low confidence" When the video is ambiguous or the codebase context is missing, the agent will stop and ask for confirmation rather than making changes it is unsure about.
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.
- 3d ago First seen · 84 lines · 0 tokens per session scan A c596b603afd1
fix is a command published in the GitHub repository mnvsk97/eyeroll (17 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 531 tokens. 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
frontend
Injects context of all relevant cli files.
cleanup-back-to-main
Go back to main and clean up the branch.
context
项目上下文管理：初始化 .context 目录、记录决策日志、压缩归档、查看历史.
spec-research
需求 → 约束集（并行探索 + OPSX 提案）.
spec-design
Create comprehensive technical design for a specification.
release
Ship a stable cmux release built by CI: bump version, update changelog, open a PR, merge, tag, then GitHub Actions builds, signs, and publishes.