A codebase scouting step that maps the files, modules, and coding patterns relevant to a proposed task. A codebase is the project's source code and supporting files.

Use it to inspect the relevant slice of a project, identify files and modules the task may affect, and write a scouting report under docs/scout.

Starting work without knowing where related code and constraints live can lead to changes in the wrong places or conflict with existing patterns. This creates a report for later research and specification work.

scout — Skill by friedbotstudio

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/friedbotstudio/baseline/scout

Any agent

npx skills add friedbotstudio/baseline --skill scout

Clone the repo

git clone --depth 1 https://github.com/friedbotstudio/baseline

Made for: Claude Code, Codex.

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,796 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.

Model	Per session	Once invoked
Fable 5	$0.00090	$0.01796
Opus 5	$0.00045	$0.00898
Sonnet 5	$0.00018	$0.00359
Haiku 4.5	$0.00009	$0.00180

Measured 2d ago against content hash 5c985075255c, 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.

.claude/skills/scout/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are mapping the slice of the codebase that matters for the current task — no more, no less. The scout report is consumed downstream by /research and /spec.

Prereqs

.claude/state/workflow.json exists.
intake is in completed OR in exceptions. If neither, stop and direct the user to invoke intake.

Inputs

The intake document at docs/intake/<slug>.md — read Problem and Goal first; they define scope.
The BRD at docs/brd/<slug>.md if present — In/Out scope lists.
The codebase at the project root.
Optional argument: a specific path to scope the scout.

If no intake exists (ad-hoc invocation), fall back to the parent task description and note in the report that the scout ran without a structured intake.

Method

Reconcile against the workspace corpus before discovering anything. This step is gated — check the flag FIRST:
```
node .claude/skills/workspace/cli.mjs flags   # gates on memory.workspace.enabled — read the `workspace:` line
```
false (the default, and the value for any project that has not opted in) → skip the rest of this step entirely and go to step 1. A populated corpus must not change scout's behaviour for a project that never asked for it.

true → if docs/system/elements/ holds any element, this scout run is a reconciliation, not a rediscovery:
```
node .claude/skills/workspace/cli.mjs reconcile --touched <comma,separated,paths> --json   # wraps workspace/reconcile.mjs -> reconcile
```
mode: "reconcile" → report the returned delta (changed / unreferenced) for the slice being touched and go straight to step 3; the corpus already answers "what is this system". mode: "discovery" → the corpus is absent or empty, so fall through to step 1 and scout normally.

The delta carries exactly those two keys. added and stale are deliberately absent from reconcile.mjs: added would need a prior reconcile snapshot that does not exist, and staleness is decided per element by classify, which /memory-sync Step 0e surfaces. Reporting a field the helper never returns is how a scout report comes to describe a delta nobody computed.

Read the full file on GitHub · 139 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.

2d ago First seen · 139 lines · 90 tokens per session scan A 5c985075255c

Subscribe to this mod's changes

scout is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,796 once invoked, about $0.0005 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.

AI Safety Planning Security Writing and docs ai ai-coding ai-governance ai-security ai-tools

dev-standards

Enforces development workflows, quality gates, coding standards, and release processes for the deterministic-agent-control-protocol project. Use when implementing features, fixing bugs, refactoring architecture, adding integrations, updating policies, writing tests, updating documentation, or preparing releases.

elliot35/deterministic-agent-control-protocol · 56 tokens

scout

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Prereqs

Inputs

Method

What this file has done since we first saw it

Other skills, from other repositories

dev-standards

code-review-with-lsp

i18n-check

vue-best-practices

python-review

rust-review