Borrowing it
Nothing to install: this file belongs to matteing/opal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/matteing/opal/main/.claude/skills/docs/SKILL.mdgit clone --depth 1 https://github.com/matteing/opalWrote 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/matteing/opal/docs)<a href="https://agentmods.dev/skills/matteing/opal/docs"><img src="https://agentmods.dev/badge/skills/matteing/opal/docs/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/skills/matteing/opal/docs"><img src="https://agentmods.dev/badge/skills/matteing/opal/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.00569 |
| Opus 5.5 | $0.00019 | $0.00228 |
| Sonnet 5.5 | $0.00009 | $0.00114 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
docs 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 2mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Skill
You maintain the docs/ directory as the source of truth for how Opal works. Each major feature or subsystem gets an evergreen explainer that stays current as the code changes.
When to act
- A feature is added, significantly changed, or removed → update or create the relevant doc.
- The user explicitly asks to document something.
- A pull request changes behavior described in an existing doc.
Format guidelines
Write docs that are right-sized — long enough to be useful, short enough to actually be read.
- Start with a one-paragraph overview of what the feature does and why it exists.
- Show the interface (tool schema, function signature, config keys) before explaining internals.
- Use Mermaid diagrams for pipelines, data flow, and architecture — never ASCII art. Wrap in
```mermaidfenced blocks. - Include a "How it works" section with just enough detail to debug or extend the feature. Skip implementation trivia.
- End with a References section linking to external sources, blog posts, papers, or benchmarks that informed the design. Always include references the user has provided.
- No timestamps or version numbers — the doc describes the current state, not a changelog.
File organization
docs/
├── ARCHITECTURE.md # System-level overview
├── tools/
│ ├── edit.md # Edit tool (hashline, str_replace history)
│ └── ... # One file per major tool or tool concept
├── agent-loop.md # Agent execution model
├── compaction.md # Context compaction
├── supervision.md # OTP supervision tree
└── ... # One file per subsystem
Place tool docs in docs/tools/. Place subsystem docs directly in docs/.
Style
- Write for a developer who knows the language but not the codebase.
- Prefer concrete examples over abstract descriptions.
- Use code blocks for schemas, configs, and short snippets.
- Keep headings to 3 levels max (##, ###, no ####).
- Link to source files when referencing specific modules (e.g.
lib/opal/tool/edit_lines.ex).
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.
- 2mo ago First seen · 55 lines · 47 tokens per session scan A cf7022b1742e
docs is a skill published in the GitHub repository matteing/opal (62 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 569 once invoked, about $0.0002 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 2026-08-30.
docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| docsmatteing/opal | Skill | 62 | 2mo ago | MIT | A | 47 | Claude Code |
| building-agentsericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 85 | Claude Code, Codex |
| agent-evalericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 79 | Claude Code, Codex |
| code-reviewdamianvtran/local-operator | Skill | 229 | yesterday | MIT | A | 45 | Claude Code, Codex |
| browser-qadamianvtran/local-operator | Skill | 229 | yesterday | MIT | A | 45 | Claude Code, Codex |
| design-qadamianvtran/local-operator | Skill | 229 | yesterday | MIT | A | 50 | Claude Code, Codex |
| engineering-principlesdamianvtran/local-operator | Skill | 229 | yesterday | MIT | A | 42 | Claude Code, Codex |