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/edwardangert/docs-agent-plugin/make-examplesgit clone --depth 1 https://github.com/EdwardAngert/docs-agent-pluginWhat 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 | $0.00009 | $0.00570 |
| Opus 5 | $0.00005 | $0.00285 |
| Sonnet 5 | $0.00002 | $0.00114 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
make-examples 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Code Examples
Review the documentation file at $ARGUMENTS and add or improve code examples.
Follow ${CLAUDE_PLUGIN_ROOT}/skills/docs-assist/reference/code-examples.md for the method: examples that are safe and consistent with the rest of the docs, anchored to the .docs-assist/reference.yml registry.
Process
1. Analyze the Document
- Read the document and identify its content type (concept, doc, guide, reference, etc.)
- Find sections that would benefit from code examples
- Identify existing examples that could be improved
2. Determine What Examples to Add
Look for:
- Procedures without corresponding code
- Concepts that would be clearer with examples
- Configuration options without sample values
- API/CLI references without usage examples
- Troubleshooting steps without commands
3. Create Examples
Follow these rules:
Safety
- All examples must be copy-paste ready
- Never use dangerous commands without safeguards
- Use documentation IP ranges (192.0.2.0/24, 198.51.100.0/24, 203.0.113.0/24)
- Use clearly fake values that won't accidentally work (example.com, your-api-key, etc.)
Consistency
- Match the style of existing examples in the codebase
- Use the same variable names, paths, and patterns as other docs
- Read
.docs-assist/reference.ymland use itsexample-variablevalues, or follow apointerentry if one fits. If the registry is absent, offer to create it seeded from values already used across the docs, and add any new placeholder you introduce. The plugin maintains this file. Seecode-examples.md. - If the repo has example conventions, follow them
Formatting
- Always include language tags on code blocks
- Combine related commands with
&& - Don't put multiple separate commands in one fenced block
- Add brief annotations above or below complex examples
Completeness
- Show the expected output where helpful
- Include error cases for troubleshooting docs
- Provide both minimal and complete examples when appropriate
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.
- yesterday First seen · 77 lines · 9 tokens per session scan A d8db514f9c87
make-examples is a command published in the GitHub repository EdwardAngert/docs-agent-plugin (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 9 tokens to every session and 570 once invoked, about $0.0000 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.