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 skills add arbiterForge/codeArbiter --skill ca-prunegit clone --depth 1 https://github.com/arbiterForge/codeArbiterWrote 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/skills/arbiterforge/codearbiter/ca-prune)<a href="https://agentmods.dev/skills/arbiterforge/codearbiter/ca-prune"><img src="https://agentmods.dev/badge/skills/arbiterforge/codearbiter/ca-prune/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/skills/arbiterforge/codearbiter/ca-prune"><img src="https://agentmods.dev/badge/skills/arbiterforge/codearbiter/ca-prune.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 | $0.00045 | $0.01637 |
| Opus 5.5 | $0.00018 | $0.00655 |
| Sonnet 5.5 | $0.00009 | $0.00327 |
| Haiku 4.5 | $0.00005 | $0.00164 |
Grade A, and why
ca-prune 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 1mo 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 1mo ago First seen · 101 lines · 45 tokens per session scan A 8949caa6008b
ca-prune is a skill published in the GitHub repository arbiterForge/codeArbiter (149 stars, last pushed today), licensed AGPL-3.0. It adds 45 tokens to every session and 1,637 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
brain-dump
Ultra-frictionless stream-of-consciousness capture for ADHD minds. Accepts raw unstructured text and parses it into discrete vault items — bugs, tasks, features, ideas, business thoughts, personal errands, learning goals, creative sparks. Works across ALL life domains, not just code. Use when the user says "brain…
morning-briefing
Start-of-day briefing for ADHD workflow. Shows what happened since last session, surfaces stale/blocked items across ALL life domains (dev, business, personal, learning, creative), recommends focus items, and proactively nudges about forgotten things. Use when the user says "good morning", "what's up", "brief me"…
session-heartbeat
Use this skill when the user asks "where are we", "status check", "health check", "checkpoint", "what have we done", or any progress review of the current session. Also use when the user wants to switch tasks, drop current work for something urgent, pause to review scope, or says the context/session is getting long.…
nested-agent-control
Control nested single-job subagents without overrunning thread capacity. Use when the user asks for nested agents, subagents, bug-factory style one-agent-one-job delegation, review coordinators, multi-agent build/review/proof loops, or when prior agent loops hit thread limits and need disciplined orchestration.
handover-writer
Use when approaching context limits (70%+ usage), switching tasks mid-stream, ending a session with incomplete work, or when the user says "write a handover", "save progress", "I need to stop", or "context is getting full". Also use proactively when you detect that context compression has started occurring.
park
Fast guilt-free shelving of vault items you're not doing right now. Preserves context and sets an optional reminder date. Works for dev items, business tasks, personal errands, learning goals — anything in the vault. Use when the user says "park this", "not now", "shelve it", "put it aside", "I'll do this later", or…