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-batchgit 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-batch)<a href="https://agentmods.dev/skills/shortcuts/radin/radin-batch"><img src="https://agentmods.dev/badge/skills/shortcuts/radin/radin-batch/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-batch"><img src="https://agentmods.dev/badge/skills/shortcuts/radin/radin-batch.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 | $0.00051 | $0.00420 |
| Opus 5.5 | $0.00020 | $0.00168 |
| Sonnet 5.5 | $0.00010 | $0.00084 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
radin-batch 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.
What it actually says
Backlog Batch
Step 1: Plan or implement
Ask with one AskUserQuestion: Plan each task first or Implement directly. Skip the question when the invoking prompt already says which
("skip planning", "just implement").
Step 2: Run the loop
Read RADIN_LIB/radin-run.md in full now and follow it as this skill's body.
Re-read it after any compaction.
No-plan rule
Step 1's answer sets one flag for every task-next call and every
task-report --next call.
Plan each task first: pass--plan-first. A task with no plan then comes back askind planning: delegate planning — unconditionally, with no judgment of the task's size or shape. Planning happens here, one task before its own execution dispatch, so the plan is written against the tree the previous tasks' commits already left behind, and the plan file it leaves on disk is the whole handoff. Dispatch its prompt like any other.STATUS: PLANNED: re-runtask-next --plan-first "<task id>", which now hands out the execution prompt.STATUS: BLOCKED (FACT|DECISION): route per Clarifying Ambiguity, then re-run the task.
Implement directly: pass no flag. Every task then comes back askind execution, whatever its size or shape, and a task with no plan implements from the entry text alone. A task with a plan still follows it.
Reply: the run loop's Phase 5 summary, verbatim; nothing is skill-specific.
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 First seen · 41 lines · 51 tokens per session scan A 9b74617d8167
radin-batch is a skill published in the GitHub repository shortcuts/radin (5 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 420 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
git-flow
Use when committing, branching, opening PRs, or deciding merge/branch strategy.
post-commit
Use when a code commit just landed (not wip/amend/undo) and CHANGELOG or plugin-version post-commit actions are needed.
commit-detection
Detects optimal commit type from git changes. Use when analyzing commits, determining commit type, or before committing.
implement-issue
Turn one labelled GitHub issue into one reviewed pull request, or stop with a stated reason. Use for every factory run; the message is a link to the issue.
finalise-session
Run /handover then commit and push changes to git.
team-workspace
Use to set up or work with a SHARED, git-backed team workspace for artifacts a team co-owns — team charters, strategy docs, decision records — kept strictly separate from your private reflections, which never leave your machine. Trigger phrases include "share our team charter with the team", "set up a shared…