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 V-Songbird/foundry --skill ember-skillgit clone --depth 1 https://github.com/V-Songbird/foundryWrote 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/v-songbird/foundry/ember-skill)<a href="https://agentmods.dev/skills/v-songbird/foundry/ember-skill"><img src="https://agentmods.dev/badge/skills/v-songbird/foundry/ember-skill/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/v-songbird/foundry/ember-skill"><img src="https://agentmods.dev/badge/skills/v-songbird/foundry/ember-skill.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 | $0.00148 | $0.00893 |
| Opus 5 | $0.00074 | $0.00447 |
| Sonnet 5 | $0.00030 | $0.00179 |
| Haiku 4.5 | $0.00015 | $0.00089 |
Grade A, and why
ember 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ember
Ember is the Foundry mascot: a round orange blob with a small flame on its head. The flame is its mood. Wild while Claude misbehaves, a small steady glow once the plugin has done its job. Original, drawn from scratch, never Anthropic's mascot, never a real animal. The owner approved the character and all three scenes on 2026-09-05; after that, a change to a mascot is a new ask, not a fix.
The rules come from docs/shared/adr/0006-readme-mascot-cartoon.md (local, never
committed). In short: one mascot per README, directly under the > **TL;DR**
block and above the data replay; a feeling, never a fact — no numbers, no
quoted benchmark output; pure SVG with SMIL, because a GitHub README <img>
runs no script; both themes via prefers-color-scheme; no text under 13px.
What exists
| Plugin | Scene | Script |
|---|---|---|
| hush | chatter bubbles and a log pile, the blue hush pill, a paw to the mouth, calm typing, a note in hush's shape |
docs/hush/launch/assets/ember-hush.js |
| razor | a tower of extra boxes, the green razor pill, one swipe, the package leaves with a red cross, a YAGNI tag |
docs/razor/launch/assets/ember-razor.js |
| foreman | a paper storm and the persevering face, the green Foreman pill, papers gather into one list, three ticks |
docs/foreman/launch/assets/ember-foreman.js |
Each script writes the SVG; the SVG is the artifact and ships as
<plugin>/assets/mascot.svg. The scripts, the character sheet
docs/shared/launch/assets/concepts.svg, and this skill are local-only. Nothing a
plugin runs depends on them.
How to make a scene
- Read character.md for the body, palette and accents, and animation.md for the timeline, the helpers and the traps.
- Copy the closest
docs/<plugin>/launch/assets/ember-<plugin>.jsto a new script. Keep the body block and the helpers; change only the scene around Ember. Every scene keeps the same beats on the 14 s clock, so the three read as one family. - Follow workflow.md: build to a scratch path, run the timing check, parse the XML, preview both themes, then ship and release.
What ships with it
3 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.
- today First seen · 56 lines · 148 tokens per session scan A 4aff429d24ce
ember is a skill published in the GitHub repository V-Songbird/foundry (4 stars, last pushed today), licensed MIT. It adds 148 tokens to every session and 893 once invoked, about $0.0007 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 2026-09-10.
Other skills, from other repositories
deps-audit
Use when auditing, updating, or securing project dependencies. Covers multi-language dependency detection, security vulnerability scanning, outdated package identification, unused dependency detection, and update strategies for npm, pip, cargo, and go.
git-advanced
Use when performing complex git operations -- rebasing, cherry-picking, resolving merge conflicts, bisecting bugs, managing stashes, cleaning history, or working with monorepos. Goes beyond basic commit/push/pull.
refactoring
Use when restructuring code without changing behavior -- extracting functions, renaming, moving files, reducing duplication, migrating between patterns (JS to TS, CJS to ESM), or addressing code smells. Covers safe refactoring workflows for any language.
repo-polish
Use when setting up new repositories, auditing existing ones, or preparing repos for public visibility. Generates .gitignore, .env.example, README, and LICENSE files. Detects committed secrets and flags security issues.
starter-session-audit
Use when the user asks to audit a session for uncaptured learnings. Activates on "audit this session", "session audit", "what did we miss", "end of session check", or "/starter-session-audit". Scans the conversation for corrections, preferences, decisions, and new context, then proposes where to save each.
clean-code
Use when the user writes new Python, or asks for review, refactor, or cleanup of Python code, names, comments/docstrings, functions, or tests. Applies Robert Martin's complete Clean Code catalog -- naming, functions, comments, DRY, boundary conditions, and tests -- to the code being changed.