Borrowing it
Nothing to install: this file belongs to kostadis/CampaignGenerator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kostadis/CampaignGenerator/main/.agents/skills/gap-review/SKILL.mdgit clone --depth 1 https://github.com/kostadis/CampaignGeneratorWrote 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/kostadis/campaigngenerator/gap-review)<a href="https://agentmods.dev/skills/kostadis/campaigngenerator/gap-review"><img src="https://agentmods.dev/badge/skills/kostadis/campaigngenerator/gap-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/kostadis/campaigngenerator/gap-review"><img src="https://agentmods.dev/badge/skills/kostadis/campaigngenerator/gap-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 | $0.00067 | $0.01590 |
| Opus 5.5 | $0.00027 | $0.00636 |
| Sonnet 5.5 | $0.00013 | $0.00318 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
gap-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 5d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gap review, driven from a chat
sd_narrate --gap-marking leaves the GM's own descriptions unwritten and marked
(#454). This skill runs the loop that answers them (#455) without the GM typing
shell commands — the case it exists for is a phone, over Remote Control,
where SSH and a touch keyboard are the friction.
Everything here shells out to sd_review, sd_compose and assemble. Do not
reimplement any of it in Python or in prose — those CLIs are the engine and
this skill is a face on them, which is also why a wrong answer here is a bug in
one place rather than two.
No model call belongs anywhere in this loop. Ruling a gap is the human
checkpoint the whole feature exists to create. If asked to decide which gaps
matter, or to write a gap's passage into the record, refuse and say why — the
evidence is experiments/20260907-phandalin-gm-gaps-selffill, where a model
asked to resolve its own eleven markers discarded nothing and handed both of the
GM's Order-of-the-Gauntlet lines to a player character, on the one passage the
markers had protected.
Assume a phone
This is always driven over Remote Control — the GM has stated it. So:
- Answer in prose, not tables. Column output is unreadable on a phone.
- Lead with the answer, then the detail. "Four gaps left in scene 1, none written" before any listing.
- Give tappable URLs, not instructions to construct one.
- Do not ask them to type a path. Find the session; confirm the name if ambiguous, which is a one-word reply rather than a path on a touch keyboard.
Find the session first
Narrations live at <campaign>/summaries/<YYYYMMDD>/narration/.
ls -d ~/src/campaigns/*/summaries/*/narration 2>/dev/null | tail -5
Default to the most recent, and say which one you picked in the same sentence as the answer. Only ask when two are plausible — composing the wrong session writes files, so an ambiguous guess is worth one question, but a lone obvious candidate is not.
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.
- 5d ago First seen · 155 lines · 67 tokens per session scan A ba83f3e54bf4
gap-review is a skill published in the GitHub repository kostadis/CampaignGenerator (5 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 1,590 once invoked, about $0.0003 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 2026-10-02.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…