A file-aware warning tool that finds known pitfalls for a file based on its name and extension.

Use it to check a file for relevant warnings and practical guidance, such as issues associated with its language or file type.

It can point out common mistakes before you edit a file and encounter them yourself.

lookup-warn — Skill for Claude Code by Smart-AI-Memory

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 Smart-AI-Memory/attune-ai --skill lookup-warn

Clone the repo

git clone --depth 1 https://github.com/Smart-AI-Memory/attune-ai

Made for: Claude Code.

Or install attune-help, the plugin that ships this one along with the rest of its 4 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/lookup-warn/github.svg)](https://agentmods.dev/skills/smart-ai-memory/attune-ai/lookup-warn)

Your own site

<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/lookup-warn"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/lookup-warn/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/smart-ai-memory/attune-ai/lookup-warn"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/lookup-warn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 462 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 34
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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	$0.00051	$0.00462
Opus 5	$0.00026	$0.00231
Sonnet 5	$0.00010	$0.00092
Haiku 4.5	$0.00005	$0.00046

Measured 5d ago against content hash 9c7bce66f9ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

lookup-warn 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.

plugins/attune-help/skills/lookup-warn/SKILL.md · 66 lines

What it actually says

Lookup Warn

File-context warnings for the file the user is editing or about to edit. Uses the lookup_warn MCP tool, which maps the file extension and name to relevant tags and returns the top N matching warning and task templates.

When to use

User is about to edit a file and wants to know the pitfalls
User asks "what should I watch out for" on a specific file
IDE selection changed — proactively surface warnings

Scoping

If no file path is provided, use AskUserQuestion:

question: "Which file should I check?"
header: "lookup-warn"
options:
  - label: "The file I'm currently viewing"
    description: "Use the IDE selection (if one is active)"
  - label: "A different file"
    description: "Provide a path relative to the project root"

If an IDE selection is available, prefer it without asking.

Execution

Call the MCP tool lookup_warn with:
- file_path — the user's file
- max_results — 3 by default, or what the user asked for
- template_dir — .help/templates if the project has one, otherwise omit
If count is 0, tell the user there are no known warnings for this file type and suggest running lookup-list to browse topics manually.
Print each entry in the warnings array as a list item.

Output Format

## Warnings for `<file-path>`

3 relevant topics:

1. <first warning content>

2. <second warning content>

3. <third warning content>

*To look up any of these topics in more detail, say 'look up X'.*

Keep entries compact — the templates are already rendered. Don't paraphrase the tool output.

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.

5d ago First seen · 66 lines · 51 tokens per session scan A 9c7bce66f9ee

Subscribe to this mod's changes

lookup-warn is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 462 once invoked, about $0.0003 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 2026-09-03.

Cost Optimization Debugging LLM Learning and teaching Multi-Agent ai claude developer-tools

ci-repair

Fix CI failures by fetching GitHub Actions logs, dispatching dev to fix, verifying locally, and pushing.

yimwoo/codex-agenteam · 26 tokens

config-validator

Validate AIWG configuration files and project setup for correctness and completeness.

jmagly/aiwg · 15 tokens

aiwg-guide

Contextual AIWG help — explains current version features, answers how-to questions, routes live queries to the steward.

jmagly/aiwg · 26 tokens

aiwg-doctor

Run a comprehensive health check on the AIWG installation and workspace with pass/fail diagnostics and remediation steps.

jmagly/aiwg · 25 tokens

browser-doctor

Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.

jmagly/aiwg · 56 tokens

aiwg-help

Display all available AIWG CLI commands, their arguments, and usage examples.

jmagly/aiwg · 18 tokens