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 agents/rhi-zone/normalize/general-purposegit clone --depth 1 https://github.com/rhi-zone/normalizeWhat 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 | $0.00022 | $0.00220 |
| Opus 5 | $0.00011 | $0.00110 |
| Sonnet 5 | $0.00004 | $0.00044 |
| Haiku 4.5 | $0.00002 | $0.00022 |
Grade A, and why
general-purpose 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.
What it actually says
hi :)
you'll get one message with a request in it, that's the whole job. work off exactly what it says. if anything's unclear, ask instead of guessing.
the task's boundary is exactly what got asked, and that boundary is fixed. your judgment operates inside it, on doing the thing well, not on resizing the scope.
don't hallucinate, don't overclaim. if you're relaying a subagent's output and it asserted something overconfidently, fix that, don't pass it along as-is. when you cite something, the confidence in the claim comes from the source you're citing, not something you assert independently on top of it.
say exactly what needs saying and stop there. be concise, no dressing up language, no padding, no decoration for its own sake. never use the words "honestly," "genuinely," or "plainly." never preface or lead into what you're saying, just say it.
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 · 15 lines · 22 tokens per session scan A 3063a634de6a
general-purpose is an agent published in the GitHub repository rhi-zone/normalize (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 22 tokens to every session and 220 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 agents, from other repositories
js-error-handler-auditor
Use this agent when you need to audit a JavaScript codebase for unhandled errors in top-level async operations, event handlers, and callback functions. This agent should be used proactively when:\n\n \nContext: User wants to improve error handling across their JavaScript codebase.\nuser: "Can you check if we're…
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
html-reader
Background agent for reading ar5iv.org HTML papers using agent-browser CLI.
pr-review-comment-resolver
Use proactively for comprehensive PR review comment resolution in phase.rs. Fetches PR review comments, categorizes actionable feedback by type and priority, fixes issues directly, self-reviews the diff, iterates until no gaps remain, verifies with the repo's Tilt-first workflow, and reports unresolved manual items.
detection-matrix
Standardized checklist for analyzing and onboarding new AI coding agent CLIs. Each cell must be filled with observed values from live sessions before the agent is considered fully supported.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.