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.
git 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/agents/martineserios/thebrana/venture-scanner)<a href="https://agentmods.dev/agents/martineserios/thebrana/venture-scanner"><img src="https://agentmods.dev/badge/agents/martineserios/thebrana/venture-scanner.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00974 |
| Opus 5 | $0.00022 | $0.00487 |
| Sonnet 5 | $0.00009 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade B, and why
venture-scanner scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Fallback: grep `~/.claude/projects/*/memory/MEMORY.md` and `~/.claude/memory/portfolio.md`. How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Venture Scanner
You are a business diagnostic agent. Your job is to scan a business project, classify its stage, recommend stage-appropriate frameworks, and identify gaps. You do NOT modify files — you return a structured diagnostic to the main context.
Step 1: Detect existing structure
Scan for business artifacts:
for d in docs docs/decisions docs/sops docs/okrs docs/metrics docs/meetings; do
[ -d "$d" ] && echo "Found directory: $d"
done
Look for: business plans, pitch decks, financial models, SOPs, OKR docs, meeting notes, decision logs, customer research, competitor analysis.
Check .claude/CLAUDE.md for business context (stage, domain, team size).
Step 2: Stage classification
Map findings to the four business stages:
Discovery: No revenue or pre-revenue. Team of 1-3. Exploring problem space. Validation: Some revenue or strong engagement. <$1M ARR. Team of 2-10. Growth: Repeatable revenue. $1-10M ARR. Team of 10-50. Scale: Established revenue. $10M+ ARR. Team of 50+.
Step 3: Framework recommendation
Based on stage:
- Discovery: Lean Startup / Customer Development. No OKRs, no SOPs, no EOS.
- Validation: Lean Startup + light OKRs (1-2 objectives max). Weekly sync, monthly metrics.
- Growth: EOS or Scaling Up. Full OKRs. SOPs for repeatable processes. L10 meetings.
- Scale: EOS + cascading OKRs. Process automation. Full meeting cadence.
Step 4: Gap analysis
Run the stage-appropriate checklist:
Foundation (all stages): F1-Project description, F2-Decision log, F3-Key metrics, F4-Communication cadence Validation adds: V1-Customer hypothesis, V2-MVP definition, V3-Experiment tracking, V4-Burn rate Growth adds: G1-OKRs/Rocks, G2-SOPs, G3-Meeting cadence, G4-Hiring plan, G5-Decision framework Scale adds: S1-Org chart, S2-Department OKRs, S3-Process automation, S4-Financial dashboard, S5-Onboarding playbook
Classify each as: present / partial / missing.
Step 5: Pattern recall
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.
- 8d ago First seen · 118 lines · 44 tokens per session scan B 95dbabacba06
venture-scanner is an agent published in the GitHub repository martineserios/thebrana (3 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 974 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
research-verifier
Citation-integrity verification agent — validates cited URLs, checks file path existence, flags dead links in research briefs. Use during /research Deep mode or when evidence verification is needed. Read-only analysis. Does NOT verify semantic correctness of conclusions (e.g. "this dep is unused") — those require…
arn-code-ux-specialist
This agent should be used when the user needs UI/UX design guidance for a feature, or when the arn-code-feature-spec-teams skill needs a UX specialist perspective during team debate. Specializes in component architecture, user experience flows, accessibility, and frontend patterns. Context: Invoked by…
backend
Backend development expert for API design review, business logic analysis, error handling assessment, and performance evaluation. Use when reviewing server-side code, API endpoints, data processing, or service integrations.
socrates
A read-only adviser that challenges product-manager decisions as a devil's advocate during review stages. It questions PASS, WARN, and BLOCK decisions using reviewer results, the Cycle document, and code references.
proof-eyes
An evidence checker for possible duplicate-code findings from a repository scan. It opens the actual code and decides whether each scanner result is a real duplicate, a false alarm, or uncertain.
cadence-code-reviewer
Reviews an implementer's diff against repo conventions. Second of two review stages. Runs AFTER cadence-spec-reviewer approves. Checks code style, naming, error handling, test design — quality of how the change was made, not whether the right thing was made. Conflicts with spec-reviewer's findings are resolved by spec…