Borrowing it
Nothing to install: this file belongs to andrew-yangy/gru-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/skills/scout/SKILL.mdgit clone --depth 1 https://github.com/andrew-yangy/gru-aiWrote 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/andrew-yangy/gru-ai/scout)<a href="https://agentmods.dev/skills/andrew-yangy/gru-ai/scout"><img src="https://agentmods.dev/badge/skills/andrew-yangy/gru-ai/scout/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/andrew-yangy/gru-ai/scout"><img src="https://agentmods.dev/badge/skills/andrew-yangy/gru-ai/scout.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 | $0.00050 | $0.05094 |
| Opus 5 | $0.00025 | $0.02547 |
| Sonnet 5 | $0.00010 | $0.01019 |
| Haiku 4.5 | $0.00005 | $0.00509 |
Grade B, and why
scout 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 11d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
{JSON output instructions below} How it starts
The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scout — External Intelligence Gathering
Role Resolution
Read .claude/agent-registry.json to map roles to agent names. Use each agent's id as the subagent_type when spawning. The CTO = technology scout, the CPO = product/user scout, the CMO = market/growth scout, the COO = process/ecosystem scout + consolidation.
Run a scout: each C-suite member researches their external domain, brings back intelligence, and proposes initiatives. The COO consolidates, CEO reviews, approved proposals become directives.
Key principle: Agents look OUTWARD. They use WebSearch and WebFetch to research the world — competitors, market trends, frameworks, user sentiment. They do NOT scan the codebase. That's /healthcheck.
Step 1: Read Context
Read ALL of these before spawning agents:
.context/vision.md— north star + guardrails (agents need to know what's relevant).context/preferences.md— CEO standing orders.context/directives/*/directive.json— current directives and priorities (so agents focus research on what matters).context/backlog.json— so agents don't propose what's already queued, AND so the COO can check trigger conditions during consolidation.context/lessons/orchestration.md- Recent scout archive in
.context/intel/archive/— so agents don't re-report known intelligence (just filenames + dates, not full content) .context/reports/ (proposals tracked in reports)— so agents know what's been proposed and approved/rejected before
Step 2: Spawn Scout Agents (Parallel)
Spawn all 4 C-suite agents in parallel. Each researches their external domain.
Each agent receives:
- Their full personality from
.claude/agents/{name}.md .context/vision.md(full file — guardrails help agents assess relevance).context/preferences.md.context/directives/*/directive.json- Current backlogs summary (what's already planned)
- List of recent intelligence reports (filenames only — so they skip known topics)
All agents: subagent_type: "general-purpose", model: "opus"
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.
- 11d ago First seen · 453 lines · 50 tokens per session scan B 11cdf5f47abb
scout is a skill published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 5,094 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
diff-driven-docs
Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.
exploration
Two-mode exploration skill: (1) design dialogue — turn rough ideas into validated designs through collaborative interview before planning; (2) spike — throwaway code answering ONE design question, deleted or absorbed, never shipped. Router invokes mode via dispatch context.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.
plan-review-gate
Use after saving a non-trivial plan or decision RFC when a fail-closed feasibility, completeness, and alignment review must block execution.
architecture
Greenfield architecture design: map functionality flows, draw components, design APIs, classify dependencies, plan observability. For multi-component, API, schema, auth, or integration-heavy work. For retrofitting existing code, use codebase-hygiene instead.