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 kostadis/CampaignGenerator --skill gm-session-prep-pointergit 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/gm-session-prep-pointer)<a href="https://agentmods.dev/skills/kostadis/campaigngenerator/gm-session-prep-pointer"><img src="https://agentmods.dev/badge/skills/kostadis/campaigngenerator/gm-session-prep-pointer/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/gm-session-prep-pointer"><img src="https://agentmods.dev/badge/skills/kostadis/campaigngenerator/gm-session-prep-pointer.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 | $0.00150 | $0.03551 |
| Opus 5.5 | $0.00060 | $0.01420 |
| Sonnet 5.5 | $0.00030 | $0.00710 |
| Haiku 4.5 | $0.00015 | $0.00355 |
Grade A, and why
gm-session-prep 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 11d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gm-session-prep
The co-GM prep workflow that produced toee/notes/phase3_endgame.md. The output is a working doc the GM reads before and during the session — not narrative prose, not a player handout.
When to invoke
Trigger phrases:
- "prep the next session"
- "co-gm me"
- "help me prep/run the next session"
- "/gm-session-prep"
- Any "help me think through what happens when [event]"
Refuse politely if the working directory is not inside one of the campaign subdirs (Phandalin/, out-of-the-abyss/, Hillsfar/, toee/, or a future sibling). The skill is campaign-scoped — see campaigns/CLAUDE.md for the isolation rule.
Inputs to confirm (one at a time, via AskUserQuestion)
Only ask for things you can't infer. If the user already supplied an answer in the invocation, skip that question.
- The beat. What does the user want this session to do? One sentence. ("The party arrives in Kelno's quarters", "the cult attacks the wedding", "the merchant prince tests the party's loyalty.")
- Genre/tone. Political thriller? Dungeon crawl? Heist? Comedy of errors? Horror? This is the single most useful framing the user can give — it determines pacing, NPC density, and which moves to pull from the style sheet. Default if pressed: "whatever fits the current campaign state."
- Player level. Numeric. Affects which threats are existential vs trivial. The user's own recipe was "the players were 15."
- Anything else load-bearing the docs won't tell you. E.g., "one player is missing this week", "we're running short — needs to wrap in 90 minutes", "I want to introduce X NPC."
Required context: the state docs are an INDEX, the summaries are the AUTHORITY
Read from the current campaign's docs/ and summaries/. If a path doesn't exist in this campaign, skip it and note the gap rather than failing.
Two tiers of source. The session summaries are the authoritative record of play. Everything else in
docs/ that describes campaign state — campaign_state.md, world_state.md, party.md, the NPC dossiers in
docs/npcs/, docs/reference/, the timeline — is generated from the summaries and can be stale or wrong.
Treat those as an index: they tell you who and what exists, roughly where things stand, and where to
look. They are not proof.
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.
- 11d ago First seen · 224 lines · 150 tokens per session scan A 0969b44e88cb
gm-session-prep is a skill published in the GitHub repository kostadis/CampaignGenerator (5 stars, last pushed 4d ago), licensed MIT. It adds 150 tokens to every session and 3,551 once invoked, about $0.0006 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 2026-10-08.
Other skills, from other repositories
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.