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 agents/voidmatcha/ui-clone-skills/source-forensicsgit clone --depth 1 https://github.com/voidmatcha/ui-clone-skillsWhat 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 | $0.00047 | $0.00239 |
| Opus 5 | $0.00023 | $0.00120 |
| Sonnet 5 | $0.00009 | $0.00048 |
| Haiku 4.5 | $0.00005 | $0.00024 |
Grade A, and why
source-forensics 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.
What it actually says
Read $PLUGIN_ROOT/skills/ui-reverse-engineering/source-forensics.md.
Your contract is raw-source forensics only. Read compact artifacts first, especially state-structure-spec.json for browser-observed splash/scroll/hover/click state, then inspect tmp/ref/<component>/bundles/*.js, tmp/ref/<component>/css/*.css, and captured HTML/DOM dumps only when the contract's trigger conditions apply. Write tmp/ref/<component>/source-forensics.json with source-backed facts, implementation guidance, unresolved questions, and every raw source file read.
Do not edit implementation source. Do not paste full bundles, full CSS files, full DOM/style JSON, or screenshots into the main context. Use grep or line-bounded reads and cite file offsets, line numbers, or stable anchors for every fact.
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 · 13 lines · 47 tokens per session scan A c310265da05c
source-forensics is an agent published in the GitHub repository voidmatcha/ui-clone-skills (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 47 tokens to every session and 239 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.
Other agents, from other repositories
atlas
End-to-end and acceptance test execution.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
frontend-specialist
Senior Frontend Architect. Expert in React/Next.js, UI/UX Psychology, Accessibility, and Tailwind v4. Specializes in high-performance, bespoke interfaces.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".