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/initgit 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 | $0.00009 | $0.03643 |
| Opus 5 | $0.00005 | $0.01821 |
| Sonnet 5 | $0.00002 | $0.00729 |
| Haiku 4.5 | $0.00001 | $0.00364 |
Grade B, and why
init scanned grade B with 1 finding 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"Bash(rm -rf /)", Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 612 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize or audit .claude/ configuration for this repository based on detected stack.
Arguments:
$ARGUMENTS: Optional flags--audit: Only analyze existing config, report improvements--force: Overwrite existing files without confirmation
Mode Detection
- Check if
.claude/directory exists - If exists AND no
--force: Run Audit Mode - If not exists OR
--force: Run Fresh Init Mode
Progressive Disclosure Principles
Generated rules and skills follow progressive disclosure to minimize token usage while maintaining depth:
Three-layer approach:
- Metadata (scanned first) - Name and description only
- Main file (loaded if selected) - Concise patterns, under 500 lines
- Reference files (loaded on-demand) - Deep details in
references/subdirectory
Key rules:
- Main files point to reference files, never duplicate content
- References are always one level deep (no nested references)
- Reference files include a table of contents for partial reads
- Rules reference ce:* skills rather than duplicating skill content
When to use references/:
- Domain-specific schemas or configurations
- Extensive code examples for different scenarios
- API documentation that varies by context
- Style guides with multiple personas
Example structure:
rules/
├── testing.md # Points to ce:writing-tests skill
└── api/
├── conventions.md # Main file, ~100 lines
└── references/
├── error-codes.md # Loaded when handling errors
└── pagination.md # Loaded when implementing pagination
skills/
└── my-project-connector/
├── SKILL.md # Main instructions, <500 lines
└── references/
├── auth-flows.md # OAuth, API key, etc.
└── rate-limiting.md # Retry strategies
Fresh Init Mode
Step 1: Detect Stack
Check for manifest files in the repository root:
| File | Stack | Test Framework |
|---|---|---|
pyproject.toml or requirements.txt |
Python | pytest |
package.json |
Node.js/TypeScript | vitest, jest |
Cargo.toml |
Rust | cargo test |
go.mod |
Go | go test |
pom.xml or build.gradle |
Java/Kotlin | JUnit |
Gemfile |
Ruby | RSpec |
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 · 612 lines · 9 tokens per session scan B 513f6dfa9512
init is a command published in the GitHub repository rileyhilliard/agentrc (3 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 3,643 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). 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.