scout

scout is a skill for Claude Code, Codex from duthaho/skillhub. It costs 192 tokens per session (1,924 once invoked), scanned A, original, MIT.

A research skill that compares your project with other software projects solving the same problem. It examines their activity, user requests, releases, documentation, and source code when deeper evidence is needed.

In plain words
What is it for?
Use it to find relevant peer repositories, investigate what their users want, and decide which lessons to adopt or skip.
Why use it?
It helps you learn from comparable projects before choosing features or design changes, while avoiding copying ideas without evidence.

Skill for Claude CodeCodex

Part of the research plugin — 7 skills shipped together

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

Made for: Claude Code, Codex.

Or install research, the plugin that ships this one along with the rest of its 7 skills.

Wrote 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.

agentmods badge for scout

README.md
[![agentmods](https://agentmods.dev/badge/skills/duthaho/skillhub/scout.svg)](https://agentmods.dev/skills/duthaho/skillhub/scout)
Your own site
<a href="https://agentmods.dev/skills/duthaho/skillhub/scout"><img src="https://agentmods.dev/badge/skills/duthaho/skillhub/scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 192 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,924 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 $0.00192 $0.01924
Opus 5 $0.00096 $0.00962
Sonnet 5 $0.00038 $0.00385
Haiku 4.5 $0.00019 $0.00192

Measured 5d ago against content hash 67d63905ea40, 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 5d 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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

scout — know the neighbors before building blind

/scout — find peer projects, then reconnoiter them /scout <owner/repo> [...] — reconnoiter exactly these peers /scout deep <owner/repo> — one peer, source-level (clone + file:line evidence)

Answer one question: what have the projects solving this same problem learned that we haven't — and which of those lessons deserves to exist here? Both halves matter: a scout that only returns "features to copy" is just an automated parity trap. The deliverable is judgment: adopt this, skip that, and the evidence either way.

Step 0 — Know thyself first

Recon of others starts with a fix on your own position:

  • Read this repo's AGENTS.md (the map skill writes it), README, and its own issue tracker's top-reacted open requests. Distill: the project's job in one sentence, and its differentiation axis — the thing it does that peers don't, which every later verdict is judged against.
  • Read out/scout/tracker.md if it exists: peers already scouted, verdicts already made. A feature SKIPped with a reason isn't re-litigated unless the evidence changed; repeat runs open with "Since last scout" — new releases, new high-reaction requests, verdicts due for revisit.
  • "Similar" means same problem, not same tech stack — a peer in another language that owns your problem space teaches more than a same-framework neighbor that doesn't.

Step 1 — Find the peers (skip when the user names them)

Discover candidates keyless, then rank by signals that resist gaming:

  • GitHub topics overlap (/repos/{o}/{r}/topics, then /search/repositories?q=topic:X) and README/description keyword search.
  • Registry keyword co-occurrence — npm /-/v1/search?text=keywords:..., PyPI JSON — projects sharing your package keywords.
  • Awesome lists and "alternatives to X" directories for the long tail.

Rank by recent push cadence, download counts (api.npmjs.org / pypistats.org), and dependents (deps.dev) — never by raw stars; star counts are purchasable and four-figure HN threads document the fake-star economy. Present the candidates with one line each on why they qualify; settle on 3–6 peers. Fewer, studied properly, beats a survey.

Read the full file on GitHub · 151 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 151 lines · 192 tokens per session scan A 67d63905ea40

Subscribe to this mod's changes

scout is a skill published in the GitHub repository duthaho/skillhub (9 stars, last pushed 12d ago), licensed MIT. It adds 192 tokens to every session and 1,924 once invoked, about $0.0010 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.

Related

Other skills, from other repositories