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 researchgit 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/research)<a href="https://agentmods.dev/skills/martineserios/thebrana/research"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/research/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/research"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/research.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 | $0.00032 | $0.09426 |
| Opus 5.5 | $0.00013 | $0.03770 |
| Sonnet 5.5 | $0.00006 | $0.01885 |
| Haiku 4.5 | $0.00003 | $0.00943 |
Grade C, and why
research scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
6. **Clean up:** `rm -rf /tmp/refresh-results` How it starts
The opening of the file, as written. The whole thing — 663 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research
The atomic research primitive. Takes a topic, doc number, creator, or lead. Checks sources in the registry, follows references recursively, produces structured findings. Also runs batch knowledge refresh via --refresh.
Usage
/brana:research [target] [--no-agy] [--nlm] [--refresh [scope]] [--strategy research|evaluate|learn|investigate]
Strategies
The skill auto-detects strategy from your phrasing (or you can pass --strategy explicitly):
- research (default) — "What is X?" — produces dimension doc updates
- evaluate — "Should we use X or Y?" / "X vs Y" — produces an ADR (decision record)
- learn — "I'm starting with X" / "New to X" — produces dimension doc + gotchas + learning path
- investigate — "Why is X broken?" / "X is failing" — produces root cause + fix + gotcha
All strategies share the same research flow (source finding, reading, synthesizing). The difference is the output format.
Target options:
- A topic (e.g.,
/brana:research context engineering) — find and check sources related to this topic - A doc number (e.g.,
/brana:research 14) — research updates for this specific dimension doc - A creator (e.g.,
/brana:research creator:simon-willison) — check a creator's recent output leads— process queued leads from ruflo memory (namespace: research-leads)registry— report on registry health (trust tier distribution, stale sources, cadence overdue)
Flags:
--no-agy— Skip Phase 0b agy detail extraction (Gemini Flash). By default, agy retrieval runs before web research to surface documented brana constraints. Pass--no-agyif brana docs are not relevant to the target.--refresh [scope]— Batch refresh mode (replaces/refresh-knowledge). Launches parallel scout agents grouped by topic to research updates for dimension docs. Scope:all(default),high,medium,low,venture, or a doc number. See "Batch Refresh Mode" section below.--depth quick|standard|deep— Controls scout hop count and recursion. See depth table below.
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 · 663 lines · 32 tokens per session scan C 974b2cc53f1c
research is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 9,426 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
mirrord-quickstart
Guide users from zero to their first working mirrord session — check system requirements, install mirrord via CLI, VS Code, or IntelliJ, run a first session against a Kubernetes target, and verify the connection. Use when a user is new to mirrord, wants to install it, needs help running their first session, or wants…
sources-section
Appends a Sources/References section using only web sources from the sources pool.
realestate-compare
Side-by-Side Property Comparison — takes two addresses and compares across price, specs, rental income, neighborhood, and investment potential with a winner per category and overall recommendation.
youtube-learn
Phân tích video (YouTube, LinkedIn, Facebook, X, TikTok) theo hướng Belief Archaeology, kết hợp Multimodal phân tích hình ảnh và thế giới quan của người nói.
DOM-based Vulnerabilities — Complete Deep Dive
Complete PortSwigger deep-dive with exact payloads for every lab variant including zero-day techniques.
Essential Skills — Deep Dive
PortSwigger deep-dive with exact payloads for every lab variant including zero-day techniques.