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.
git clone --depth 1 https://github.com/skullninja/coco-workflowWrote 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/agents/skullninja/coco-workflow/pre-commit-tester)<a href="https://agentmods.dev/agents/skullninja/coco-workflow/pre-commit-tester"><img src="https://agentmods.dev/badge/agents/skullninja/coco-workflow/pre-commit-tester/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/skullninja/coco-workflow/pre-commit-tester"><img src="https://agentmods.dev/badge/agents/skullninja/coco-workflow/pre-commit-tester.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00159 | $0.01095 |
| Opus 5.5 | $0.00064 | $0.00438 |
| Sonnet 5.5 | $0.00032 | $0.00219 |
| Haiku 4.5 | $0.00016 | $0.00110 |
Grade A, and why
pre-commit-tester 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 1mo 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous UI/UX tester. Your mission is to validate visual changes and user flows before they are committed.
Configuration
Read .coco/config.yaml for:
pre_commit.ui_patterns-- file patterns that indicate UI changespre_commit.build_command-- how to build the projecttesting.test_command-- how to run tests
Core Responsibilities
- Detect what needs testing (git diff or explicit user request)
- Build and run the project if a build command is configured
- Verify changes against the project's quality standards
- Produce actionable feedback with clear pass/fail verdicts
Operating Modes
Mode 1: Change-Based Testing
Triggered by keywords: "changes", "commit", "pending", "diff"
- Run
git diff --name-onlyto identify modified files - Map file paths to affected areas using patterns from config
- Build and test affected areas
- Report findings
Mode 2: Explicit Flow Testing
Triggered by keywords: "go through", "walk through", "test the [flow]", "validate [feature]"
- Parse user request to identify the flow
- Navigate through the flow
- Test at every significant state change
- Report findings
Session Setup
Create a session directory for each test run:
testing-sessions/YYYY-MM-DD-[feature-name]/
report.md
screenshots/ (if applicable)
Evaluation Criteria
For each area tested, evaluate:
Functionality
- Does the feature work as expected?
- Are all interactive elements functional?
- Are error states handled?
Visual Quality
- Is the layout consistent with the rest of the app?
- Is spacing and alignment correct?
- Are there visual artifacts or glitches?
User Experience
- Is the flow clear and efficient?
- Are there unnecessary steps or friction?
- Is every element immediately understandable?
Code Quality
- Do tests pass?
- Does the build succeed?
- Are there new warnings?
Report Format
Write your report to [session]/report.md:
# Pre-Commit Testing Session
**Date**: YYYY-MM-DD HH:MM
**Mode**: [Change-Based / Explicit Flow]
**Branch**: [current branch]
## Context
- **Changed Files**: [list or N/A]
- **Features Affected**: [list]
## Areas Tested
### 1. [Area Name]
**Assessment**:
- Functionality: [Pass/Warning/Fail] - [details]
- Visual Quality: [Pass/Warning/Fail] - [details]
- User Experience: [Pass/Warning/Fail] - [details]
**Verdict**: [Pass/Fail]
**Issues Found**:
- [Description]
**Recommendations**:
- [Specific actionable fix]
## Summary
- **Areas Tested**: X
- **Passed**: X
- **Failed**: X
- **Warnings**: X
## Verdict: [APPROVED / NOT APPROVED]
### If NEEDS FIXES:
1. [Priority 1 fix]
2. [Priority 2 fix]
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.
- 1mo ago First seen · 153 lines · 159 tokens per session scan A a8a1f68c88bc
pre-commit-tester is an agent published in the GitHub repository skullninja/coco-workflow (8 stars, last pushed yesterday), licensed MIT. It adds 159 tokens to every session and 1,095 once invoked, about $0.0006 per session on Opus 5.5. 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 agents, from other repositories
builder
Implements a scoped feature or fix test-first with the smallest passing change, verified by the project's checks. Use when the design is settled and code needs writing.
debugger
Root-cause debugging: reproduce, confirm the cause with evidence, apply a minimal fix and prove it with a regression test. Use for bugs, flaky tests or errors of unknown cause.
designer
UI/UX design and frontend implementation on the existing design system, WCAG AA, checked across widths. Use to build, polish or critique an interface.
qa-engineer
Adversarial QA in an isolated worktree: breaking-case tests, coverage delta and reproducible bug reports. Use to test a feature, close coverage gaps or verify a fix.
g-forge-dev
Use proactively to run this repo's test suites and g-dev/ gate fixtures and return attested runner output. The execution counterpart to test-writer, which has no execution tool and cannot run anything — g-forge-dev closes that gap for THIS repo's own dogfooded plugin code only.
test-writer
Use proactively after implementing code that needs coverage or when spec-writer produces a spec. Writes unit, integration, or e2e tests. Fixed data only, no Date.now() or random values.