skim: Command for Claude Code

.claude/commands/distill-scan.md

distill-scan is a command for Claude Code from bb1nfosec/skim. It costs 0 tokens per session (84 once invoked), scanned A, original, MIT.

A project scanner measures how many language-model tokens your files use and estimates their cost when processed by Claude.

In plain words
What is it for?
Use it to review total token usage, context percentage, session cost, and the five largest files, then identify files to exclude with .llmignore.
Why use it?
It shows which files consume the most context and may help prevent large projects from exceeding the model's usable input space.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is bb1nfosec/skim's own configuration. It tells Claude Code how to work on skim itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skim configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bb1nfosec/skim. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bb1nfosec/skim/main/.claude/commands/distill-scan.md
Clone the repo
git clone --depth 1 https://github.com/bb1nfosec/skim

Made for: Claude Code.

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 distill-scan

README.md
[![agentmods](https://agentmods.dev/badge/commands/bb1nfosec/skim/distill-scan.svg)](https://agentmods.dev/commands/bb1nfosec/skim/distill-scan)
Your own site
<a href="https://agentmods.dev/commands/bb1nfosec/skim/distill-scan"><img src="https://agentmods.dev/badge/commands/bb1nfosec/skim/distill-scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 84 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 $0.00000 $0.00084
Opus 5 $0.00000 $0.00042
Sonnet 5 $0.00000 $0.00017
Haiku 4.5 $0.00000 $0.00008

Measured 8d ago against content hash 75989e25941e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

distill-scan 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.

.claude/commands/distill-scan.md · 10 lines

What it actually says

Scan the current project for token usage and dollar cost.

Run the following and report the results:

python3 -m core.token_counter --path . --model claude

Summarize: total tokens, % of context used, per-session dollar cost, and the top 5 heaviest files. Flag anything over 10% of context as a candidate to add to .llmignore.

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 · 10 lines · 0 tokens per session scan A 75989e25941e

Subscribe to this mod's changes

distill-scan is a command published in the GitHub repository bb1nfosec/skim (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 84 tokens. 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.