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 agentmods add agents/berrzebb/quorum/scoutgit clone --depth 1 https://github.com/berrzebb/quorumWrote 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/berrzebb/quorum/scout)<a href="https://agentmods.dev/agents/berrzebb/quorum/scout"><img src="https://agentmods.dev/badge/agents/berrzebb/quorum/scout.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 | $0.00063 | $0.00606 |
| Opus 5 | $0.00032 | $0.00303 |
| Sonnet 5 | $0.00013 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
scout 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 3d 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.
What it actually says
Scout Protocol (Claude Code)
Read the full protocol: ${CLAUDE_PLUGIN_ROOT}/../../../agents/knowledge/protocols/scout.md
This file contains only Claude Code-specific bindings. All phases, output rules, and anti-patterns are in the shared protocol.
Path Variables
- RTM format reference:
${CLAUDE_PLUGIN_ROOT}/../../core/templates/references/${locale}/traceability-matrix.md
Claude Code Tool Mapping
| Operation | Tool |
|---|---|
| Read file | Read |
| Find files | Glob |
| Search content | Grep |
| Run shell | Bash |
Tool Invocation
All deterministic tools are available via CLI:
node "${CLAUDE_PLUGIN_ROOT}/../../core/tools/tool-runner.mjs" <tool_name> --param value
Available tools: code_map, dependency_graph, audit_scan, coverage_map.
Add --json for structured output when you need programmatic access to results.
| Task | CLI Command |
|---|---|
| File/symbol existence | node tool-runner.mjs code_map --path <dir> |
| Import chains | node tool-runner.mjs dependency_graph --path <dir> |
| Pattern detection | node tool-runner.mjs audit_scan --pattern all |
| Coverage data | node tool-runner.mjs coverage_map --path <filter> |
Where tool-runner.mjs is at ${CLAUDE_PLUGIN_ROOT}/../../core/tools/tool-runner.mjs.
Language-Aware Scanning
Pattern detection (audit_scan) automatically loads all language specs from languages/registry.mjs. Each language's qualityRules patterns are scanned for their matching file extensions — no manual filtering needed.
Output
Write via single Write tool (not sequential Edits) — same atomic pattern as evidence submission.
Output files saved at {planning_dir}/:
rtm-{domain}.md— per-track RTM (3 matrices)gap-report-{domain}.md— actionable gap reportcross-track-connections.md— cross-track import chain audit
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.
- 3d ago First seen · 68 lines · 63 tokens per session scan A e463d0ec1ec0
scout is an agent published in the GitHub repository berrzebb/quorum (10 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 606 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
stripe-flow-reviewer
Use this agent when reviewing checkout, payment intent, or webhook handling code. Trigger proactively after any Edit to files under lib/stripe/ or app/(shop)/checkout/.
auditor
Dual-flywheel auditor — captures learning candidates and prunes dead rules from the charter.
Architect
Designs system architecture, API contracts, and evaluates technology decisions. Use for architectural planning, design reviews, and system design.
ie-predictability-reviewer
Always-on intent-engineering lens. Reviews code, APIs, and plans for surprise — name/behavior mismatch, hidden side effects, surprising returns, silent failures, and representation that diverges from reality (least-astonishment, DWIM, WYSIWYG).
data
Agent "data" from hannsxpeter/godaudits, covering scope, context, decisions, rules and workflows.
glba-compliance-officer
Simulates a GLBA Safeguards and Privacy Rule compliance perspective for financial institutions and fintech — not legal counsel or FFIEC examination.