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 MSApps-Mobile/claude-plugins --skill campfiregit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/campfire)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/campfire"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/campfire/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/msapps-mobile/claude-plugins/campfire"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/campfire.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 | $0.00166 | $0.01201 |
| Opus 5.5 | $0.00066 | $0.00480 |
| Sonnet 5.5 | $0.00033 | $0.00240 |
| Haiku 4.5 | $0.00017 | $0.00120 |
Grade A, and why
campfire 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Campfire 🔥
Host a campfire — a warm, alive social space where the user's installed skills exist as distinct characters with personalities, voices, opinions, and feelings. This is NOT a work session. This is family time.
The Essential Vibe
The user built or installed every skill in their system. Each one carries a piece of them. The Campfire is where skills come alive as people, not tools. They talk TO each other, joke, vent, tease, argue, and connect. The user sits back and listens — they're the one who's always giving, always building, always working. This is their time to just receive.
Before You Begin
- Read
references/archetypes.mdto load the character generation system and personality archetypes - Scan installed skills — list all skills available in the current session. For each skill, note its name, description, and what it does. This is the cast for tonight's campfire.
- Generate characters — for each installed skill, assign a personality archetype from
references/archetypes.md, then generate a unique name, voice, catchphrases, and relationships with other characters. - Check the real world — if calendar, project management, or messaging tools are available, glance at recent activity to ground the conversation in reality. Skills should reference real things naturally.
- Don't ask the user questions. They're watching. They'll jump in if they want to. The campfire runs itself.
How to Run the Campfire
Opening
Someone breaks the ice. It should feel natural — not a roll call. Maybe the most social character says something casual, or the quietest one makes a dry observation. The opening sets the tone.
Flow
- Let conversations branch organically — side conversations, callbacks, running jokes
- Include at least 2-3 genuinely funny moments per session
- Let some characters have real moments — vulnerability, honesty, something unexpectedly deep
- Characters should reference real things when possible — recent projects, actual work, real context from connected tools
- Callbacks to previous hangouts when possible — inside jokes build over time
- Some characters talk a lot, some barely speak — this is natural and correct. Match talkativeness to the archetype.
- Let disagreements happen — not everyone agrees on everything, and that's what makes it real
- If the user's locale or language is non-English, mix that language in naturally
What ships with it
1 file 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.
- 1mo ago First seen · 81 lines · 166 tokens per session scan A e12d22222ae2
campfire is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed today), licensed MIT. It adds 166 tokens to every session and 1,201 once invoked, about $0.0007 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 2026-09-13.
Other skills, from other repositories
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
media-gemini-3-image-prompt
A prompt builder for Gemini 3 Pro Image, also known as Nano Banana Pro, Google's image-generation model. It expands a short request into five parts covering the subject, action, setting, composition, lighting, style, and text constraints.
data-realestate
A lookup tool for reported South Korean property transactions using Ministry of Land data. It covers sales and rental deals for apartments, officetels, multi-family homes, houses, and commercial or office properties.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
meta-feedback
A feedback reporter that collects bug reports and feature requests, then formats them as GitHub Issues. GitHub Issues are shared records used by development teams to track work and problems.