Borrowing it
Nothing to install: this file belongs to Insight-Services-APAC/ingenious. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Insight-Services-APAC/ingenious/main/.claude/commands/ai-config/prune-claude-md.mdgit clone --depth 1 https://github.com/Insight-Services-APAC/ingeniousWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/insight-services-apac/ingenious/prune-claude-md)<a href="https://agentmods.dev/commands/insight-services-apac/ingenious/prune-claude-md"><img src="https://agentmods.dev/badge/commands/insight-services-apac/ingenious/prune-claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/insight-services-apac/ingenious/prune-claude-md"><img src="https://agentmods.dev/badge/commands/insight-services-apac/ingenious/prune-claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00525 |
| Opus 5 | $0.00000 | $0.00262 |
| Sonnet 5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
prune-claude-md 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 4d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prune CLAUDE.md
Reduce CLAUDE.md to only the most essential information for effective agent performance. Target: 300 lines maximum.
Principles for Pruning
Keep information that:
- Directly affects code generation (coding standards, patterns to follow)
- Prevents common mistakes (critical gotchas, forbidden patterns)
- Enables task completion (how to build, test, run)
- Is unique to this project (not general knowledge)
Remove information that:
- Claude already knows (general best practices, language syntax)
- Is redundant or repeated
- Is too verbose when a shorter version suffices
- Describes obvious project structure
- Contains examples that can be inferred from code
Step 1: Analyze Current Size
wc -l CLAUDE.md
Step 2: Categorize Content by Priority
Priority 1 - Must Keep:
- Project-specific commands (build, test, run)
- Critical constraints or requirements
- Non-obvious architectural decisions
- Environment setup essentials
Priority 2 - Keep if Space Allows:
- Code style preferences beyond linting
- Common gotchas specific to this codebase
- Key file locations for important modules
Priority 3 - Remove:
- General programming advice
- Lengthy explanations of standard tools
- Verbose examples when terse ones work
- Aspirational guidelines not enforced
Step 3: Apply Compression Techniques
- Consolidate related points into single concise statements
- Use bullet points instead of paragraphs
- Remove filler words and unnecessary qualifiers
- Replace examples with patterns where possible
- Link to docs instead of duplicating documentation
- Use code blocks sparingly - only for non-obvious commands
Step 4: Restructure for Scanning
Organize remaining content:
# CLAUDE.md
## Quick Reference (commands, key paths)
## Constraints (must-follow rules)
## Patterns (how things are done here)
## Gotchas (common mistakes to avoid)
Step 5: Validate Final Size
wc -l CLAUDE.md
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.
- 4d ago First seen · 78 lines · 0 tokens per session scan A ed7ec4dfdf19
prune-claude-md is a command published in the GitHub repository Insight-Services-APAC/ingenious (24 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 525 tokens. 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 2026-09-04.
Other commands, from other repositories
remote-autopilot-install.v1
Remotely install Stakpak Autopilot on any reachable Linux host over SSH, with optional AWS/GCP/Azure VM discovery or provisioning: /remote-autopilot-install.
requirement-review
A command that has several specialized agents review a requirements document and produce a revised version through a controlled workflow.
add-api-railway
Create a new Express API endpoint with full integration.
add-charts
Integrate Chart.js or Recharts for data visualization. Create reusable chart components: line, bar, pie, area, scatter. Implement responsive sizing with container-based dimensions. Add interactive tooltips showing detailed data on hover. Create customizable legends with click-to-hide series. Support real-time data…
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.