A review tool that examines an agent conversation for opportunities to create new reusable skills or improve existing ones. It writes a Markdown report and can hand the work to a skill-creation tool.

Use it to review the current conversation or an earlier transcript, identify missing or improvable skills, and document the recommendations.

It helps capture useful ways of working before they are forgotten after a coding session.

skill-scout — Skill for Claude Code by donnfelker

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.

Any agent

npx skills add donnfelker/donnfelker-plugin-marketplace --skill skill-scout

Clone the repo

git clone --depth 1 https://github.com/donnfelker/donnfelker-plugin-marketplace

Made for: Claude Code.

Or install skill-scout, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/donnfelker/donnfelker-plugin-marketplace/skill-scout/github.svg)](https://agentmods.dev/skills/donnfelker/donnfelker-plugin-marketplace/skill-scout)

Your own site

<a href="https://agentmods.dev/skills/donnfelker/donnfelker-plugin-marketplace/skill-scout"><img src="https://agentmods.dev/badge/skills/donnfelker/donnfelker-plugin-marketplace/skill-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/donnfelker/donnfelker-plugin-marketplace/skill-scout"><img src="https://agentmods.dev/badge/skills/donnfelker/donnfelker-plugin-marketplace/skill-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 204 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,454 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00204	$0.05454
Opus 5.5	$0.00082	$0.02182
Sonnet 5.5	$0.00041	$0.01091
Haiku 4.5	$0.00020	$0.00545

Measured 2mo ago against content hash cdb7189d372c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill-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 2mo 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.

plugins/skill-scout/skills/skill-scout/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Scout

Scout an agent conversation for skill opportunities before the lessons evaporate.

When to use this skill

Trigger when the user asks for a retrospective on the agent conversation itself — extracting skills from it, finding skill gaps, learning from how the session went. Do not trigger for general code retrospectives, work summaries, or PR descriptions. This skill is specifically about turning conversation behavior into reusable skill content.

The process

Source the conversation — current one by default, or a past .jsonl transcript under ~/.claude/projects/ when the user asks to scout a previous session
Inventory available skills — repo plugins, then user-level skills, then any marketplaces the user names
Detect signals — five categories, described below
Produce a report — structured markdown, output directly in chat
Hand off — to /skill-creator for new skills, or Edit the affected SKILL.md for existing ones

Step 1 — Source the conversation

There are three ways in. Pick based on what the user asked for.

Default — the current conversation. Claude already has the turns in context; just read them as you would any other context — no file I/O needed. This is the common case, used whenever the user says "scout this conversation", "this session", or doesn't specify.

Explicit past-session request. When the user points at an earlier conversation — "recommend skills from my previous session", "scout yesterday's chat", "what skills would have helped in that earlier session" — the turns are not in context, so read them from the saved transcripts under ~/.claude/projects/. Claude Code stores one directory per project (the working-directory path with every / replaced by -) holding one .jsonl per session.

Start with the current project unless the user clearly means a different repo:

ENCODED=$(pwd | sed 's|/|-|g')
ls -lt ~/.claude/projects/$ENCODED/*.jsonl 2>/dev/null | head -10

Read the full file on GitHub · 277 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.

2mo ago First seen · 277 lines · 0 tokens per session scan A cdb7189d372c

Subscribe to this mod's changes

skill-scout is a skill published in the GitHub repository donnfelker/donnfelker-plugin-marketplace (4 stars, last pushed 4mo ago), licensed MIT. It adds 204 tokens to every session and 5,454 once invoked, about $0.0008 per session on Opus 5.5. 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.

Building agents

skill-scout next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skill-scoutdonnfelker/donnfelker-plugin-marketplace	Skill	4	4mo ago	MIT	A	204	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code