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-recordgit 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-record)<a href="https://agentmods.dev/skills/shortcuts/radin/radin-record"><img src="https://agentmods.dev/badge/skills/shortcuts/radin/radin-record.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 | $0.00100 | $0.02004 |
| Opus 5 | $0.00050 | $0.01002 |
| Sonnet 5 | $0.00020 | $0.00401 |
| Haiku 4.5 | $0.00010 | $0.00200 |
Grade A, and why
radin-record 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 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.
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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record to Backlog
Turn feedback, bugs, follow-ups, and ideas from the live session into
backlog entries that survive past the conversation. This captures what a
human said — radin-review logs what a diff revealed; radin-plan and
radin-execute consume the backlog afterward.
All writes go through the shared CLI at
$HOME/.claude/.radin/lib/radin-backlog.sh — it owns the index's schema and
resolves the per-project namespace, so never hand-edit a backlog file or
compute its path yourself.
Step 1: Decide what to log
The instruction after /radin-record sets the scope:
- Specific ("add the auth timeout bug"): log exactly that item, nothing else.
- Generic ("add the findings", bare
/radin-record): scan the whole session for anything a reasonable person calls a bug, follow-up, idea, or feedback — including "we should probably..." asides nobody wrote down. Each distinct item becomes its own entry.
Stay faithful to what was actually said. This is a capture tool: log only what the conversation raised, worded close to how it was raised.
One raised thing can be several sequential pieces of work ("add rate limiting on top of new auth middleware" needs the middleware first). Log each piece as its own entry — split by the work's shape, not the user's phrasing.
When scope or split is genuinely unclear, invoke /grilling on that point
and let the user settle it before logging — mid-scan too. Distinguish that
from an item that is real but not yet sharp (clear boundary, fuzzy work —
"figure out caching at some point"): log it as a stub — short title, a body
saying plainly it's unspecified and what's known so far. radin-plan
sharpens it when someone picks it up; grilling now has nothing concrete to
grill about.
Step 2: Chart each item's open decisions — MANDATORY, do not skip silently
The user is at the keyboard now; radin-execute may later run with nobody
behind it. This is the only point in the whole flow where that's true — settle
judgment calls here so execution never has to. Skipping this step is the
single biggest way this skill fails: an item that looks "obvious" to you
still needs the check below before it's allowed to skip.
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.
- 2d ago Changed · +13 lines 4431446510bd
- 7d ago First seen · 157 lines · 100 tokens per session scan A b69c7cdc5e35
radin-record is a skill published in the GitHub repository shortcuts/radin (5 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 2,004 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
git-flow
Use when committing, branching, opening PRs, or deciding merge/branch strategy.
managing-product
Extracts product requirements and produces a PRD. Use when a user wants to build software and needs to define what to build before architecture or implementation, when scoping an MVP, or when translating a vague idea into a buildable specification.
orchestrating-work
Principles for multi-agent workflow execution. Use when coordinating agents, accepting or rejecting agent work, executing producer-critic cycles, or running any multi-phase orchestrated task.
run-agent
Launch and supervise Claude Code or Codex through the CCAM Run API. Use when the user wants to start a monitored agent, select a model, approval policy, sandbox, or working directory, send a follow-up, inspect live output, resume a native session, or stop a dashboard-launched run.
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).