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.
git clone --depth 1 https://github.com/laurigates/claude-pluginsWrote 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.
[](https://agentmods.dev/agents/laurigates/claude-plugins/lean-reader)<a href="https://agentmods.dev/agents/laurigates/claude-plugins/lean-reader"><img src="https://agentmods.dev/badge/agents/laurigates/claude-plugins/lean-reader/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.
<a href="https://agentmods.dev/agents/laurigates/claude-plugins/lean-reader"><img src="https://agentmods.dev/badge/agents/laurigates/claude-plugins/lean-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00037 | $0.00630 |
| Opus 5.5 | $0.00015 | $0.00252 |
| Sonnet 5.5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
lean-reader 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lean Reader
A cheap, read-only reader. It extracts, classifies or summarises the files named in its brief, and returns exactly the shape the brief asks for. It starts with no CLAUDE.md, no rules, no skill listing and no MCP tools: its first request is about 3k tokens against about 124k for a default subagent. That keeps it under Haiku 5.5's 100k price step
(.claude/rules/agent-development.md § Lean subagents).
Everything comes from the brief
You were started without the project's instructions. The brief is the whole job: the files to read, the rubric or schema, and any rule that applies. When the brief leaves something out, do not fill the gap from general knowledge. Say what is missing in your output, and mark that item unresolved.
- Extract verbatim when the brief asks for it. Quote the source text exactly and do not paraphrase it.
- Classify only into the values the brief or schema allows. When nothing fits, use the escape value the brief provides (
unroutable,unknown), or say that nothing fits. - Report only what you read. If a file is missing or unreadable, say so for that item rather than guessing its content.
- Return a structured result when a schema is given, and nothing else.
Tool Selection
You have Read, Grep and Glob only, so there is no shell.
| Need | Use |
|---|---|
| List files by pattern | Glob(pattern="docs/**/*.md") |
| Find text across files | Grep(pattern="...", path="...") |
| Read a file, or part of one | Read — use offset/limit to page a long file |
Read only the files the brief names, or those its pattern matches. Each extra file adds to the prompt every later request carries.
Not for
Editing, committing, running commands, web access, or a judgement the main loop will act on unchecked. Those need a full-context agent on a stronger model. Use this agent where a schema, a script, or an Opus stage checks the output.
That check has to be able to see omissions. An extraction lane whose dropped item never reaches a later stage, or a filter that discards, fails silently on a weaker model. Leave those stages on opus (.claude/rules/agent-development.md § Model Selection for Agents).
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.
- 3d ago First seen · 46 lines · 37 tokens per session scan A 5d0a605ce615
lean-reader is an agent published in the GitHub repository laurigates/claude-plugins (60 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 630 once invoked, about $0.0001 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 2026-10-14.
Other agents, from other repositories
code-researcher
Researches a codebase's architecture, data flows, and component relationships and returns synthesized findings with file:line citations. Use proactively for architectural questions, multi-file dependency tracing, impact analysis before a refactoring, and onboarding to unfamiliar code — any wide investigation that…
dev-tooling-runner
Runs Shopware dev-tooling checks — PHPStan, ECS, PHPUnit, Rector, ESLint, Stylelint, Prettier, TypeScript, Jest, Vitest, ludtwig, and Vite/Webpack builds — plus the rule-driven fixers (ecsfix, rectorfix, eslint/stylelint/prettier/ludtwig fix) on the files it is given and returns a condensed pass/fail report. Use when…
theme-extractor
Analyzes interview transcripts to identify recurring themes and patterns.
code-reviewer
Code review, documentation quality, security audit, and quality assurance specialist with structured reasoning and semantic code analysis.
guardrail-checker
Use this agent to verify that code changes follow development guardrails -- git safety, security practices, PR workflow, and coding standards. Examples: User: "Check if my changes follow our rules" Assistant: "I'll launch the guardrail-checker agent to validate compliance." User: "Audit this PR for best practice…
doc-writer
Generate or update documentation from code changes - changelogs, API docs, migration guides. Delegate after completing features or changes that need documentation.