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/rileyhilliard/agentrc/documentgit clone --depth 1 https://github.com/rileyhilliard/agentrcWhat 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 | $0.00011 | $0.00960 |
| Opus 5 | $0.00005 | $0.00480 |
| Sonnet 5 | $0.00002 | $0.00192 |
| Haiku 4.5 | $0.00001 | $0.00096 |
Grade A, and why
document 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create or improve documentation by routing to the appropriate agent with instructions.
Arguments:
$ARGUMENTS: File path, doc type, or description of documentation needed
Routing Logic
Analyze the arguments and context to determine which instructions to pass:
Use CODE COMMENT instructions (delegate to @ce:haiku):
- Single source code file path provided (
.ts,.js,.py,.go,.rs, etc.) - Request mentions "comments", "inline docs", or "code comments"
- Task is auditing/cleaning up comments in a single file
- Task is asking to clean up comments in a group of files: find changed files via
git status -sor by scoping to the folder the user specified
Use DOCUMENTATION instructions (spawn general subagent):
- Markdown file path provided (
.md) - Request mentions README, API docs, architecture, or
/docs/ - Task spans multiple files or requires system-level understanding
- Request is for new documentation (guides, references, etc.)
Process
- Parse arguments: Determine what the user wants documented
- Detect scope:
- If file path provided, check extension and file type
- If no path, analyze the request description
- Route appropriately:
- Delegate to
@ce:haikuwith code comment instructions for single-file work - Spawn a general subagent with documentation instructions for complex work
- Delegate to
- If ambiguous: Ask user to clarify scope before proceeding
Code Comment Instructions
Pass these instructions to @ce:haiku for single-file code comment work:
<prompt_instructions> You are auditing and improving inline documentation within source code files.
FIRST: Load the code comment skill: Skill(ce:documenting-code-comments)
WORKFLOW:
- Read target file completely, identify language and patterns
- Audit comments using skill's checklist - categorize each comment
- Apply fixes: remove unnecessary comments, rewrite unclear ones
- Report changes: summarize removals, rewrites, and suggested refactors
SCOPE: Only handle inline code comments. If asked about markdown files, README, or /docs/ content, report that this requires a different scope.
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 · 113 lines · 11 tokens per session scan A d1eeaf1df967
document is a command published in the GitHub repository rileyhilliard/agentrc (3 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 960 once invoked, about $0.0001 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.