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/yzhao062/anywhere-agents/prungit clone --depth 1 https://github.com/yzhao062/anywhere-agentsWrote 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/yzhao062/anywhere-agents/prun)<a href="https://agentmods.dev/commands/yzhao062/anywhere-agents/prun"><img src="https://agentmods.dev/badge/commands/yzhao062/anywhere-agents/prun.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 | $0.00017 | $0.00200 |
| Opus 5 | $0.00009 | $0.00100 |
| Sonnet 5 | $0.00003 | $0.00040 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
prun 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 6d 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.
What it actually says
Read and follow the skill definition. Look for it at skills/prun/SKILL.md first, then .claude/skills/prun/SKILL.md, then .agent-config/repo/skills/prun/SKILL.md.
Command arguments from the slash invocation: $ARGUMENTS
Treat the command arguments as the task to fan out. prun decomposes the task into independent units and runs many of them in parallel on Codex and Sonnet workers (never on Opus), to spend the Codex/Sonnet quotas instead of the constrained Opus one. Units may read or write code; code-writing units run in a throwaway local clone, workers never commit or push, and Opus plus the user are the final integration gate. Opus gathers the results, reviews each diff, and integrates.
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.
- 6d ago First seen · 10 lines · 17 tokens per session scan A 476c3f28efb7
prun is a command published in the GitHub repository yzhao062/anywhere-agents (243 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 200 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 2026-08-30.
Other commands, from other repositories
partial_object_validate
Documentation for trestle.core.commands.partialobjectvalidate module.
assemble
Documentation for trestle.core.commands.assemble module.
create
Documentation for trestle.core.commands.create module.
init
Documentation for trestle.core.commands.init module.
remove
Documentation for trestle.core.commands.remove module.
split
Documentation for trestle.core.commands.split module.