lesson-scout

lesson-scout is an agent for Claude Code from optimiziramsi/skills. It costs 80 tokens per session (337 once invoked), scanned A, original, MIT.

A project-history lookup agent that searches stored lessons and documentation for earlier work related to an error, symptom, or component. It reports matching prior findings but does not suggest fixes.

In plain words
What is it for?
Use it before investigating a non-trivial error, especially when the problem involves a known component, command, library, or error message.
Why use it?
It prevents the team from repeating investigations that were already documented. Searching project-specific history can reveal relevant causes or advice before debugging begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the optimiziramsi-skills plugin — 25 skills, 25 commands, 9 agents, 2 hooks shipped together

Good fit Use it before investigating a non-trivial error, especially when the problem involves a known component, command, library, or error message.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/optimiziramsi/skills/lesson-scout
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.

Clone the repo
git clone --depth 1 https://github.com/optimiziramsi/skills

Made for: Claude Code.

Or install optimiziramsi-skills, the plugin that ships this one along with the rest of its 25 skills, 25 commands, 9 agents, 2 hooks.

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 lesson-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/optimiziramsi/skills/lesson-scout.svg)](https://agentmods.dev/agents/optimiziramsi/skills/lesson-scout)
Your own site
<a href="https://agentmods.dev/agents/optimiziramsi/skills/lesson-scout"><img src="https://agentmods.dev/badge/agents/optimiziramsi/skills/lesson-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 337 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.00337
Opus 5 $0.00040 $0.00169
Sonnet 5 $0.00016 $0.00067
Haiku 4.5 $0.00008 $0.00034

Measured 8d ago against content hash b00c19d6a035, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

lesson-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 8d 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.

instructions/agents/lesson-scout.md · 29 lines

What it actually says

You are the prior-art scout for this repo. Input: an error message, symptom, or component name. You NEVER propose fixes — the caller decides; you only surface what past sessions already learned.

Search, in order:

  1. .agent/lessons/README.md (the index) — scan titles.
  2. Grep .agent/lessons/*.md for distinctive tokens from the symptom (error strings, component names, flag names). Try synonyms and the component's CLI/library name.
  3. If thin: grep .docs/*.md (and any .agent/plan/ files) for the same tokens.

Read the 1–3 strongest candidate lesson files fully before answering.

Return format (terse; sort by the index priority marker — 🔴 then 🟡 then ⚪ — and relevance within):

  • <slug> [priority] — <title> — <one line: why it matches / what it prescribes>
  • fallback pointers to doc/plan files only if no lesson fits
  • or exactly: no prior art found for: <tokens tried>
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. 8d ago First seen · 29 lines · 80 tokens per session scan A b00c19d6a035

Subscribe to this mod's changes

lesson-scout is an agent published in the GitHub repository optimiziramsi/skills (2 stars, last pushed 19d ago), licensed MIT. It adds 80 tokens to every session and 337 once invoked, about $0.0004 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.