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 vstrapasson/rpg-marketplace --skill rpg-embate-forgegit clone --depth 1 https://github.com/vstrapasson/rpg-marketplaceWrote 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/vstrapasson/rpg-marketplace/rpg-embate-forge)<a href="https://agentmods.dev/skills/vstrapasson/rpg-marketplace/rpg-embate-forge"><img src="https://agentmods.dev/badge/skills/vstrapasson/rpg-marketplace/rpg-embate-forge/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/vstrapasson/rpg-marketplace/rpg-embate-forge"><img src="https://agentmods.dev/badge/skills/vstrapasson/rpg-marketplace/rpg-embate-forge.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 | $0.00277 | $0.01646 |
| Opus 5 | $0.00138 | $0.00823 |
| Sonnet 5 | $0.00055 | $0.00329 |
| Haiku 4.5 | $0.00028 | $0.00165 |
Grade A, and why
rpg-embate-forge 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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RPG Embate Forge — assemble a runnable non-combat challenge
What this skill is for
A desafio is the non-combat sibling of encontro: a Victory Points challenge (or a single dramatic check) resolved by skills, not swords. This skill realizes it in Foundry end-to-end — a challenge journal the GM runs from, an optional scene, the live skill-check rolls, the VP track as a clock, and a one-click runner macro that rolls the challenge for you — reusing the scene compiler but driven by the challenge's VP structure. Content comes from the desafio note body + relations; you format and run it, you don't invent the challenge.
Workflow
- Journal. Write the challenge via
create-quest-journalused generically (the only journal-create tool — seerpg-journal-forge/references/journal-mapping.md),folderName: "Challenges/<subsystem>"(e.g.Challenges/Influence— the nested path groups challenges by subsystem; foundry-mcp ≥ 0.12.0 creates the hierarchy). Prefer existing:search-journals/list-journalsby title first; if it exists,update-quest-journalinstead of duplicating. Build pages from thedesafiobody: Structure (subsystem · format ·vp_target· thresholds · per-roll awards), DCs (the DC table), Degrees & fail-forward, and a player-facing Read-aloud page. Content is HTML, not Markdown (the MCP strips Markdown) — use the quest classes:<div class="readaloud">for player text,<div class="gmnote">for GM-only,<h2 class="spaced">for sections. RecordjournalId. - Scene (conditional). If
desafio.locationresolves to alocal, delegate torpg-scene-forge(prefer existing by name, else generate-under-confirmation, then light for mood). RecordsceneId. If there is nolocal— most social/research challenges — skip scenes; a council debate needs no battlemap. - VP clock. For a VP challenge, add a clock page to the journal mirroring a
relogio(name, segments =vp_target, filled = current VP, status). Give the page a stable name and seed an initialvpflag (flags.foundry-mcp-bridge.vp = 0) so the runner macro (step 5) has a fixedpageIdto advance — the macro keeps VP authoritative in that flag and mirrors it as a ▰▱ bar in the page text. Without the macro, the clock is a journal page the GM advances by hand as VP accrue (there is no dedicated clock MCP tool); state that. Forscale: single-check, skip the clock entirely. - Live: request the rolls. For each beat,
request-player-rolls.rollType=skill(orcustomfor a formula / a skill Foundry doesn't list by that name);rollTarget= the skill (e.g.diplomacy,acrobatics,intimidation);targetPlayer= the player/character;flavor= the beat + its DC;rollModifierfor a circumstance bonus from preparation. Visibility is mandatory:request-player-rollsrequiresuserConfirmedVisibility: true, so establish public vs. private (isPublic) before each call — ask if the GM hasn't said. Map the result's degree to the VP award and narrate the fail-forward consequence; advance the clock page. (This is the manual, one-roll-at-a-time path; step 5 packages the whole loop as a hotbar macro.) - Runner macro (offer it). Install a one-click GM macro that runs the whole challenge, via the
create-macroMCP tool (foundry-mcp ≥ 0.10.0). Bake thisdesafio's data —vp_target, the award map, the beats (skill + DC), thresholds, and the clockjournalId/pageId— into the template inreferences/embate-macro.md. The macro is hybrid: on run it asks who rolls — GM rolls for the selected party (rolls each token's chosen skill, reads the degree, awards VP) or send to the players (posts an@Checkbutton, collects each player's own roll via acreateChatMessagehook) — then maps every degree of success to VP via the award map and advances the VP clock page automatically, firing threshold/fail-forward notes as VP crosses them. Offer to pin it: a globalhotbarSlot(every scene), or — when thedesafiohas alocalwhose scene was ensured in step 2 — bind it to that scene viasceneName(foundry-mcp ≥ 0.11.0) so it shows on the GM bar only while that challenge's map is open and clears on leave. Passflags.foundry-mcp-bridge.challengeId. Record the returnedmacroId. Forscale: single-check, the macro is a single roll withclock: null(no track). The macro and step 4 are two front-ends for the same rules — install the macro for re-triggerable, self-contained play; use barerequest-player-rollsfor an ad-hoc one-off. - Serialize + manifest. Serialize any scene writes (the universal parallel-write rule). Record
{ journalId, sceneId?, clockPage?, macroId?, status:"built" }in the manifestdesafiorow; a built challenge (withjournalId) is skipped on re-run. Any skill that can't be mapped to arollTypegoes toopenDecisions.
What ships with it
2 files 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.
- 11d ago First seen · 20 lines · 0 tokens per session scan A 3e933e8b130b
rpg-embate-forge is a skill published in the GitHub repository vstrapasson/rpg-marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 277 tokens to every session and 1,646 once invoked, about $0.0014 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
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
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…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
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.