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 instructions/shortcuts/radin/agents-mdgit clone --depth 1 https://github.com/shortcuts/radinWhat 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 | $0.02833 | $0.02833 |
| Opus 5 | $0.01417 | $0.01417 |
| Sonnet 5 | $0.00567 | $0.00567 |
| Haiku 4.5 | $0.00283 | $0.00283 |
Grade C, and why
radin AGENTS.md scanned grade C with 2 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 2d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| Distribution | Git repo ([github.com/shortcuts/radin](https://github.com/shortcuts/radin), currently private). Install with `curl \| bash install.sh` — downloads latest release tarball, or `main` if no release exists, Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Distribution | Git repo ([github.com/shortcuts/radin](https://github.com/shortcuts/radin), currently private). Install with `curl \| bash install.sh` — downloads latest release tarball, or `main` if no release exists, How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
radin — Agent Reference
Read this before touch any file in repo.
Project
| Field | Value |
|---|---|
| What it is | Claude Code plugin: agents + skills + install glue |
| Runtime language | None — bash only |
| Target OS | macOS and Linux |
| Supported architectures | Arch-neutral through Homebrew. Works on macOS's /opt/homebrew//usr/local and on Linuxbrew's /home/linuxbrew/.linuxbrew. No uname -m branching. Branch on command -v only where tool itself differs by OS (e.g. md5 vs md5sum). |
| Distribution | Git repo (github.com/shortcuts/radin, currently private). Install with curl | bash install.sh — downloads latest release tarball, or main if no release exists, into ~/.claude/radin. No git clone needed. Hack on radin itself: git clone + ./install.sh. |
radin gives solo dev on small Claude subscription one install for cost-optimized agentic workflow. Ships backlog-driven execution
(radin-execute, radin-plan, radin-review), installs companion
tools (rtk, caveman, code-review-graph, thermo-nuclear, ponytail) —
some unconditional, some only on explicit yes pick.
radin never vendors or forks them.
Dev loop
This repo source of truth. Any agent or skills iteration must be done in agents/*.md and skills/*/SKILL.md respectively.
- Editing radin's own agents/skills: edit
agents/*.mdorskills/*/SKILL.mddirectly.thermo-nuclearone exception — not vendored here at all.install.shdownloads itsSKILL.mdstraight from cursor/plugins at install time, same as any other companion tool. radin only vendors what it wrote itself. - Editing
install.sh, docs, or repo scaffolding: edit directly, as normal. install.shinstalls from this repo into~/.claude/agentsand~/.claude/skills. Only adds or updates files there — one direction, repo to consumer.
Storage contract
All backlog content and execution state live inside target repo itself, in one canonical directory at repo root:
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.
- 2d ago First seen · 233 lines · 2,833 tokens per session scan C 353eea28e249
radin AGENTS.md is an instructions file published in the GitHub repository shortcuts/radin (5 stars, last pushed 12d ago), licensed MIT. It adds 2,833 tokens to every session, about $0.0142 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
jira-mcp CLAUDE.md
Instructions for softspark/jira-mcp, covering jira-mcp, tech stack, commands, pre-commit gate and key conventions.
ai-sdk CLAUDE.md
Claude Code instructions for open-metadata/ai-sdk, covering claude.md - metadata ai sdk, repository structure, quick commands, linting & formatting and testing.
weeek-mcp CLAUDE.md
Claude Code instructions for YOLKINS/weeek-mcp, covering claude.md — guide for ai coding agents working on weeek-mcp, what this is, tech stack pinning, mcp invariants (do not break — even temporarily) and logging discipline.
Table-GitHub-Capability-Router AGENTS.md
Instructions for duoduoler-ops/Table-GitHub-Capability-Router: This is the canonical repository instruction file. Client-specific compatibility files must point here instead of duplicating these rules.
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.
wiki_ticket_sdd CLAUDE.md
Instructions for SpillwaveSolutions/wiki_ticket_sdd, covering acme platform, work tracking policy and work taxonomy.