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/matteing/opal/docsnpx skills add matteing/opal --skill docsgit clone --depth 1 https://github.com/matteing/opalWhat 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 | $0.00569 |
| Opus 5 | $0.00023 | $0.00284 |
| Sonnet 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 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 — 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.
- 2d ago First seen · 55 lines · 47 tokens per session scan A cf7022b1742e
docs is a skill published in the GitHub repository matteing/opal (58 stars, last pushed 20d ago), licensed MIT. It adds 47 tokens to every session and 569 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 2026-08-30.
Other skills, from other repositories
agent-pattern-verification
Verify AI agent code for dangerous patterns including infinite loops, unbounded retries, tool hallucinations, and context overflow. Use before deploying agent workflows or when reviewing agent code.
cloudflare-agent
Enable ControlKeel governance for Cloudflare Agents with policy gates, budget enforcement, PII detection, and secure execution.
controlkeel-governance
Operate inside a ControlKeel-governed session. Use this before code edits, shell execution, delegation, deploy work, or any task that needs CK validation, findings, budget, proof, or routing context.
bounded-loop
Run objective, repeatable improvement work under an immutable verifier and hard iteration, cost, time, and no-progress limits. Use for approved experiments with an automated metric and sandboxed worker.
challenge
Adversarially challenge the current plan or finding. Assume the direction is wrong and build the strongest case against it. Surfaces blind spots, false assumptions, and unexplored alternatives before execution starts.
continuity
Learn, record, audit, and apply codebase patterns consistently across a repo by comparing current code to canonical local examples stored in CK memory. Use when asked to preserve continuity, learn a pattern, check drift, fix inconsistent implementations, or enforce local conventions.