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 ur-grue/autopunk-media-skills --skill template-selectorgit clone --depth 1 https://github.com/ur-grue/autopunk-media-skillsWrote 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/ur-grue/autopunk-media-skills/template-selector)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/template-selector"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/template-selector/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/ur-grue/autopunk-media-skills/template-selector"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/template-selector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.07427 |
| Opus 5.5 | $0.00014 | $0.02971 |
| Sonnet 5.5 | $0.00007 | $0.01485 |
| Haiku 4.5 | $0.00003 | $0.00743 |
Grade A, and why
template-selector 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 1mo 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 — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Template Selector
What This Skill Does
Takes a project description and recommends which skills, agents, and workflow sequence to use — turning a 394-skill library into a short, ordered checklist for your specific project.
When To Use This Skill
- You are starting a new media project and do not know which skills from this library apply to your format
- You have a deadline and want the fastest path from concept to deliverable without browsing categories
- You are working in a format you have not used before (first podcast, first newsletter, first documentary pitch) and want a guided starting point
- Your project crosses formats (a documentary with a companion podcast and social campaign) and you need skills from multiple categories wired into a single workflow
- You are onboarding a colleague or collaborator who has never used the skill library and want to hand them a ready-made toolkit for the project
What You Need To Provide
Required:
- Project type or medium (documentary, magazine feature, podcast, YouTube channel, newsletter, investigation, PR campaign, data story, screenwriting project, radio programme, social media campaign)
- Primary deliverables (what you need to produce by the end)
- Deadline or timeline (even a rough one: "three weeks", "six months", "ongoing weekly")
Optional:
- Team size (solo, small team, large production)
- Experience level with this format (first time, some experience, veteran)
- Whether you have existing material to work from (a treatment, rough footage, interview transcripts, a dataset)
- Budget constraints that affect scope (no travel budget, no external contributors, etc.)
- Distribution channels (broadcast, streaming, print, web, email, social platforms)
- Whether the project has a companion format (podcast + newsletter, documentary + social campaign)
How the Assistant Approaches This
The assistant works through these steps in order. The goal is a focused recommendation, not a catalogue of everything the library offers.
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.
- 1mo ago First seen · 501 lines · 35 tokens per session scan A cca4f7142e31
template-selector is a skill published in the GitHub repository ur-grue/autopunk-media-skills (38 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 7,427 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
harness-binary-spelunking
Use when investigating an agent-harness CLI's internals (Claude Code, codex, opencode, or similar): extracting the system prompt or tool descriptions, finding what code path produces a specific UI message, decoding minified function names or Rust symbols, understanding undocumented config keys, or otherwise spelunking…
scope
Guide for working with Scope, a developer environment management tool that automates environment checks, detects known errors, and provides automated fixes. Use when creating Scope configurations (ScopeKnownError, ScopeDoctorGroup, ScopeReportLocation), debugging environment issues, or writing rules for error…
park
Save current work context for later resumption.
working-with-mise
Use when adding, configuring, or troubleshooting mise-managed tools - ensures proper CLI usage, detects existing config files, and diagnoses PATH/activation issues when commands aren't found.
hk-creating-checks
Use when adding, writing, or fixing a check (step) in an hk.pkl, picking a builtin or writing a custom command, declaring an effect for --safe, or when hk reports "effect is unknown", "unexpected argument '--safe'", or "Hook 'check' not found". Also use when a step's syntax differs between hk 1.x and 2.x. For…
checkout
Use when checking out a PR, branch, or ref for local work - sets up worktree with context.