scout

A set of lightweight techniques for finding unknowns before or during software work. It treats the written request as a map and the real codebase and constraints as the territory to investigate.

In plain words
What is it for?
Use it to inspect unfamiliar code, clarify decisions, test ideas with prototypes, compare references, or explain and check understanding of a problem.
Why use it?
It helps reveal missing requirements, hidden constraints, and wrong assumptions before they become expensive to fix.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/vaayne/agent-kit/scout
Any agent
npx skills add vaayne/agent-kit --skill scout
Clone the repo
git clone --depth 1 https://github.com/vaayne/agent-kit

Made for: Claude Code, Codex.

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 862 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00122 $0.00862
Opus 5 $0.00061 $0.00431
Sonnet 5 $0.00024 $0.00172
Haiku 4.5 $0.00012 $0.00086

Measured 2d ago against content hash 4896ad78ffe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

skills/scout/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scout

Distilled from Thariq's A Field Guide to Fable: Finding Your Unknowns.

Premise: the prompt and context are the map; the codebase and its real constraints are the territory. The gap between them is the user's unknowns, and work quality is bottlenecked by clarifying them — before, during, and after implementation. This skill is a toolkit, not a workflow: diagnose, pick one technique, run it inline. Produce no artifact beyond what the technique itself outputs.

Diagnose first

Before picking a technique, collect the user's starting point — experience with the domain, familiarity with this part of the codebase, where they are in their thought process. Every technique below degrades to generic output without it. Then place the unknowns:

Quadrant Signal Technique
Known knowns Already in the prompt Just work
Known unknowns "I haven't decided X yet" Interview
Unknown knowns "I'll know it when I see it" Prototypes, References
Unknown unknowns Unfamiliar domain or code area Blindspot pass first

Before implementation

  • Blindspot pass — the user doesn't know what questions to ask. Survey the territory for them: what good looks like, prior art in the repo, common potholes, the domain vocabulary. Teach, don't list — the output should upgrade their next prompt, not just enumerate gaps.
  • Brainstorm + prototypes — criteria they'd only recognize on sight. Show several genuinely different directions with fake data before wiring anything up (HTML artifact for anything visual). Also works for scope: brainstorm interventions from cheapest to most ambitious and let them react.
  • Interview — one question at a time, prioritizing questions whose answers would change the architecture. The grill skill is the heavy-duty version.
  • References — when pointing beats describing. Source code is the best reference: read the implementation they like (any language) and reimplement its semantics, not its surface.
  • Decision-first plan — order the plan by what the user is most likely to tweak: data models, type interfaces, user-facing flows on top; mechanical refactors at the bottom. The blueprint skill owns this; spec-dev for the full gated workflow.

Read the full file on GitHub · 53 lines

Changes

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.

  1. 2d ago First seen · 53 lines · 122 tokens per session scan A 4896ad78ffe0

Subscribe to this mod's changes

scout is a skill published in the GitHub repository vaayne/agent-kit (53 stars, last pushed 6d ago), licensed MIT. It adds 122 tokens to every session and 862 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens