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/patrickclery/ruly/compressgit clone --depth 1 https://github.com/patrickclery/rulyWhat 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 | $0.00018 | $0.01799 |
| Opus 5 | $0.00009 | $0.00899 |
| Sonnet 5 | $0.00004 | $0.00360 |
| Haiku 4.5 | $0.00002 | $0.00180 |
Grade A, and why
ruly:compress 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ruly:compress Command
Overview
The /ruly:compress command analyzes Claude Code markdown rule files to identify redundancies, repeated patterns, and opportunities to make the documentation more DRY (Don't Repeat Yourself). It suggests consolidation strategies and can optionally apply the improvements.
Usage
/ruly:compress <directories/files...>
Arguments
<directories/files...>- One or more markdown files or directories containing rule files to analyze
Examples
# Analyze a single file
/ruly:compress rules/workaxle/core/essential/common.md
# Analyze an entire directory
/ruly:compress rules/workaxle/core/
# Analyze multiple directories
/ruly:compress rules/workaxle/core/ rules/github/pr/
# Analyze all rules
/ruly:compress rules/
Analysis Process
1. Pattern Detection
The command identifies:
- Duplicate content blocks - Exact or near-exact text appearing in multiple files
- Similar code examples - Code snippets with minor variations that could use a template
- Repeated explanations - Concepts explained multiple times across files
- Common patterns - Frequently used structures that could be extracted
- Cross-references - Multiple files referencing the same concept
2. Redundancy Types
Content Duplication
# Found in 3 files:
"Always use Make commands, never run commands directly"
→ Suggestion: Create central command reference
Pattern Repetition
# Found in 5 files with slight variations:
Employee.dataset.not_deleted.where(company:)
→ Suggestion: Extract to common query pattern
Concept Re-explanation
# Soft-delete handling explained in:
- essential/common.md (full explanation)
- testing/specs.md (partial explanation)
- services/patterns.md (brief mention)
→ Suggestion: Single source with references
3. Compression Strategies
Strategy 1: Extract Common Patterns
- Create a central
patterns/directory for reusable patterns - Reference patterns instead of duplicating them
- REQUIRED: Add extracted file to
requires:frontmatter (see below)
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 · 306 lines · 18 tokens per session scan A 359424b7a007
ruly:compress is a command published in the GitHub repository patrickclery/ruly (5 stars, last pushed 7d ago), licensed MIT. It adds 18 tokens to every session and 1,799 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.