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/insight-services-apac/ingenious/prune-readmegit 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-readme)<a href="https://agentmods.dev/commands/insight-services-apac/ingenious/prune-readme"><img src="https://agentmods.dev/badge/commands/insight-services-apac/ingenious/prune-readme.svg" alt="Measured on agentmods" 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 | $0.00553 |
| Opus 5 | $0.00000 | $0.00277 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
prune-readme 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prune README.md
Reduce README.md to essential information for developer onboarding. Target: concise, scannable, actionable.
Principles for Pruning
Keep information that:
- Enables quick start (clone, install, run in under 5 minutes)
- Explains the purpose (what this project does, one paragraph max)
- Shows usage (basic examples, common commands)
- Points to more info (links to detailed docs, not duplicated content)
Remove information that:
- Duplicates information available elsewhere (package.json scripts, inline code comments)
- Is obvious from the code or file structure
- Contains excessive examples when one suffices
- Includes outdated badges or status indicators
- Has verbose explanations that could be one-liners
Step 1: Analyze Current Size
wc -l README.md
Step 2: Categorize Content by Priority
Priority 1 - Must Keep:
- Project name and one-line description
- Prerequisites (language version, required tools)
- Installation steps
- Basic usage/run command
Priority 2 - Keep if Space Allows:
- Configuration options (brief)
- Common troubleshooting
- Contributing guidelines (or link)
- License
Priority 3 - Remove:
- Lengthy architecture explanations (move to docs/)
- Multiple usage examples (keep one, link to more)
- Changelog content (use CHANGELOG.md)
- Verbose feature lists
- Screenshots that don't aid understanding
Step 3: Apply Compression Techniques
- Use tables for option/config documentation
- Single code block for install + run (copy-paste friendly)
- Link to docs instead of duplicating documentation
- Remove badges that don't provide useful information
- Collapse optional sections using details/summary if supported
Step 4: Restructure for Scanning
Optimal README structure:
# Project Name
One-line description
## Quick Start
Prerequisites, install, run - all in one place
## Usage
Most common command or API example
## Configuration
Table or brief list (optional)
## Documentation
Links to detailed docs
## License
One line
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 · 91 lines · 0 tokens per session scan A c344c503e85a
prune-readme 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 553 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
akb-production-review
Review AKB production-governance docs and hooks.
b00t
Show b00t hive status — git, zellij, governance gates, cake balance, open issues.
requirement-review
需求文档多角色评审（requirement-review）：需求文档 → 7-Agent 并行评审 → 重构高质量需求文档（Runtime 受控流程，0-7 阶段状态机）.
wish-review
description: Execute an end-to-end review loop for a wish, combining test execution, Death Testament aggregation, and scoring.
review
Review a change against the repository's rule-driven modern C++ contract.
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…