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 shortcuts/radin --skill radin-reviewgit clone --depth 1 https://github.com/shortcuts/radinWrote 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/shortcuts/radin/radin-review)<a href="https://agentmods.dev/skills/shortcuts/radin/radin-review"><img src="https://agentmods.dev/badge/skills/shortcuts/radin/radin-review/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/shortcuts/radin/radin-review"><img src="https://agentmods.dev/badge/skills/shortcuts/radin/radin-review.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 | $0.00092 | $0.01810 |
| Opus 5 | $0.00046 | $0.00905 |
| Sonnet 5 | $0.00018 | $0.00362 |
| Haiku 4.5 | $0.00009 | $0.00181 |
Grade A, and why
radin-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review to Backlog
Run the strict review passes against a caller-specified scope and persist
every finding the user agrees to as a backlog entry instead of terminal
output. That leaves a durable backlog radin-execute (or a human) works
through later.
Step 1: Resolve scope argument
Resolve the argument (or its absence) via the shared CLI. Don't probe git/gh by hand:
bash "$HOME/.claude/.radin/lib/radin-scope.sh" [<arg>]
It settles commit hashes, PR references, directory paths, and the no-argument default (working branch's diff against its merge-base with main/master). Route on exit code:
- 0: resolved. It prints
type/scope/commandlines; run the printed command to get the scope's content. - 1: not a commit, PR, or directory. A natural-language range ("the
last 5 commits", "since yesterday") is yours to translate into concrete
git log/git diffinvocations. Anything else: report it as unresolvable. - 2: ambiguous (candidates on stderr, e.g. both a PR number and a directory). Interactive: ask which one. Non-interactive (e.g. radin-execute's reviewer sub-agent): report both readings and stop, so the caller retries with an unambiguous scope or resolves it with the user.
State the resolved scope in one line before proceeding, e.g.
Scope: commit a1b2c3d or Scope: directory src/auth/.
Scope discipline
The resolved scope is the whole review surface. A finding qualifies only if the scope introduced it.
- Diff scope (commit, PR, branch, range): only lines the diff adds or changes. Code that already existed and the diff left alone is out of scope, even in a file the diff touches, even when it is worse than what the diff added. Read surrounding code for context, never to find findings.
- Directory scope: every file under that path, nothing outside it.
- Out-of-scope problem the diff makes worse: report it only when the in-scope change is what makes it wrong, and say which changed line causes that.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · +53 lines · +9 tokens per session 0365befb363d
- yesterday Changed · +1 lines cb68c0b43d5a
- 10d ago First seen · 128 lines · 83 tokens per session scan A afcf24d053a2
radin-review is a skill published in the GitHub repository shortcuts/radin (5 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,810 once invoked, about $0.0005 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 skills, from other repositories
challenge
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every eLicit/Verify gate. Not for code correctness (use sniper).
code-quality
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional verification (run verification FIRST, then code-quality).
elicitation
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).
react-effects-audit
Use when auditing React or Next.js components for unnecessary or unsafe useEffect usage -- detects 9 anti-patterns from "You Might Not Need an Effect".
pr-summary
Summarize current pull request with diff, comments, and changed files. Use when reviewing PRs or before merging.
sniper-check
Use when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.