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 martineserios/thebrana --skill geminigit clone --depth 1 https://github.com/martineserios/thebranaWrote 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/martineserios/thebrana/gemini)<a href="https://agentmods.dev/skills/martineserios/thebrana/gemini"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/gemini/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/martineserios/thebrana/gemini"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/gemini.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 | $0.00047 | $0.01869 |
| Opus 5.5 | $0.00019 | $0.00748 |
| Sonnet 5.5 | $0.00009 | $0.00374 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
gemini 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/brana:gemini — Gemini Worker Delegation
Delegate a task to agy (the Gemini CLI worker). Claude orchestrates; Gemini executes as a stateless worker. Every result flows back through Claude into the brana system.
Usage
/brana:gemini "task description" # inline task
/brana:gemini t-XXXX # pull task from backlog
--bg (fire-and-continue) is out of scope for v1. Full lifecycle requires Claude present when
agy finishes. Use Layer A (Bash: agy -p "...") for fire-and-forget sweeps.
agy-Eligible Task Types
| Type | Notes |
|---|---|
| Research sweep | Atomic, read-only, Gemini Flash speed |
| Boilerplate generation | ⚠️ Convention-sensitive — ruflo required |
| Doc first draft | ⚠️ Pass explicit "why" context in task description |
| Conversion/translation | Deterministic, speed matters |
| Batch summarization | Parallel, repetitive |
| Test scaffolding | ⚠️ Convention-sensitive — ruflo required |
| Competitive/market analysis | Research-heavy, brana-agnostic |
Never Delegate (Claude-native)
system/ changes · git operations · tasks.json writes · architectural decisions ·
multi-step stateful refactors · memory/session writes.
ToolSearch("select:mcp__ruflo__memory_search,mcp__ruflo__memory_store")
ROUTE
Validate the 4-question routing heuristic:
- Atomic? — completable in one
agy -pcall, no mid-task state 2a. System-isolated? — no writes to system/, git, hooks, tasks.json during execution 2b. Context-enrichable? — ENRICH can supply enough background for useful output - Speed/token benefit? — repetitive, fast, or token-heavy for Claude
If any answer is no, abort. Tell the user why and suggest the appropriate tool (Claude directly, /brana:build, /brana:research, etc.).
Hard-block for convention-sensitive task types when ruflo is unavailable:
Convention-sensitive types: boilerplate generation, test scaffolding, ADR draft.
ToolSearch query: "ruflo memory_search"
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 · 199 lines · 47 tokens per session scan A 81649176afe1
gemini is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,869 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
antigravity
Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle. Claude is the conductor/orchestrator — requirements, architecture, the hard 20%, verification, and review — and routes deterministic, high-volume work (scaffolding…
writing-quality
Audit and rewrite content to remove AI writing patterns ("AI-isms") from deliverables, emails, and any written output. Use this skill whenever generating deliverable content (Phase 1 curation in any client deliverable skill), drafting client emails longer than 3 sentences, writing proposals or SOWs, creating reports…
yellow-sheet-corpus
Run the Yellow Sheet chain end to end against ANY matter, from the original PDFs, and read the result honestly. Use whenever someone asks what has been tested end to end, whether a matter produces a usable sheet, how to onboard a NEW matter, or asks to re-run after a code change. Carries the intake mechanism that…
excel-connector-governance
Governs driving Excel Online (Business) through a Microsoft Copilot Studio agent against SharePoint-hosted .xlsx. Triggers — "Copilot Studio", "Excel Online (Business)", "add a row", "update a row", "delete a row", "connector 502 / BadGateway", "Office Script", "pin the File input", "spreadsheet agent", "SharePoint…
build-execute
Bounded execution loop for a validated build plan. Hard caps on iterations, edits, and (where applicable) spend prevent runaway loops. Each iteration runs a CONDITIONAL adversarial review (only when the change touches a contract, a pinned constant, a refusal limb, or an unmutated path), applies the edit, measures via…
search-governance
Governance for all web search and research-grade content fetching. Brave returns SNIPPETS ONLY, so never ship a Brave-only synthesis for research-shaped output. Enforces three rules — (1) Brave (bravewebsearch via MCP) is for discovery, finding URLs, while a fetch tool, a search-and-scrape tool or a headless browser…