SutroYaro: Skill for Claude Code

.claude/skills/info-defrag/SKILL.md

info-defrag is a skill for Claude Code from cybertronai/SutroYaro. It costs 45 tokens per session (787 once invoked), scanned A, original, Unlicense.

A documentation-maintenance check that scans a codebase for old numbers, outdated descriptions, broken links, and conflicting information. A codebase is the collection of files that make up a software project.

In plain words
What is it for?
For checking experiment counts, comparing duplicated methods tables, updating contributor descriptions, and verifying that project timelines cover recent work.
Why use it?
It helps catch documentation drift, where code and written information stop matching after changes are merged. This reduces the chance of using stale project facts in reports or planning.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is cybertronai/SutroYaro's own configuration. It tells Claude Code how to work on SutroYaro 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 SutroYaro configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cybertronai/SutroYaro. 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/cybertronai/SutroYaro/main/.claude/skills/info-defrag/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cybertronai/SutroYaro

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 info-defrag

README.md
[![agentmods](https://agentmods.dev/badge/skills/cybertronai/sutroyaro/info-defrag.svg)](https://agentmods.dev/skills/cybertronai/sutroyaro/info-defrag)
Your own site
<a href="https://agentmods.dev/skills/cybertronai/sutroyaro/info-defrag"><img src="https://agentmods.dev/badge/skills/cybertronai/sutroyaro/info-defrag.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 787 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 $0.00045 $0.00787
Opus 5 $0.00023 $0.00394
Sonnet 5 $0.00009 $0.00157
Haiku 4.5 $0.00005 $0.00079

Measured 8d ago against content hash 397f9e4679b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

info-defrag 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/skills/info-defrag/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Info Defrag

Scan the codebase for stale information, inconsistencies, and broken references. This catches drift that happens when experiments get merged but docs don't get updated.

What to check

1. Experiment count

The number of experiments appears in multiple files. They drift.

# Actual count
wc -l research/log.jsonl
grep -c "^| exp" DISCOVERIES.md

# Where the number appears
grep -rn "33 experiment\|34 experiment\|35 experiment\|36 experiment" docs/ CLAUDE.md README.md

Fix any file that shows a different number than the log.

2. Best methods table

CLAUDE.md and DISCOVERIES.md both have a methods ranking table. They should match.

# Compare the two
grep -A10 "Current Best Methods" CLAUDE.md
grep -A10 "DMC baseline rankings" DISCOVERIES.md

3. People descriptions

Contributors change roles. Check docs/context.md People table against recent git log.

# Who contributed recently
git log --format="%an" --since="2 weeks ago" | sort -u

If someone submitted experiments, their bio should mention it.

4. Timeline coverage

The gantt chart in docs/context.md should cover recent work.

# Last date in the timeline
grep -o "2026-[0-9-]*" docs/context.md | sort | tail -1

# Last commit date
git log --format="%ai" -1 | cut -d' ' -f1

If the gap is more than a week, extend the timeline.

5. Index pages

Check that index files list all their children.

# Catchups
ls docs/catchups/*.md | wc -l
grep -c "\.md" docs/catchups/index.md

# Sessions
ls docs/sessions/*.md | grep -v transcript | wc -l
grep -c "\.md" docs/sessions/index.md

# Findings in nav
ls docs/findings/exp*.md | wc -l
grep -c "findings/" mkdocs.yml

6. Broken file references

Check that files mentioned in docs actually exist.

# Find markdown links and check targets
grep -roh '\[.*\](\.\./[^)]*\.md)' docs/ | grep -o '(.*\.md)' | tr -d '()' | sort -u | while read f; do
  resolved="docs/$f"
  [ ! -f "$resolved" ] && echo "BROKEN: $f"
done

Read the full file on GitHub · 114 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 114 lines · 45 tokens per session scan A 397f9e4679b5

Subscribe to this mod's changes

info-defrag is a skill published in the GitHub repository cybertronai/SutroYaro (16 stars, last pushed 3mo ago), licensed Unlicense. It adds 45 tokens to every session and 787 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

rigorous-research

Conduct AI/ML research as a science - first-principles reasoning, mechanism-level hypotheses, falsifiable predictions, discriminative experiments, honest evaluation, and claims that survive hostile review. Use when starting or steering an AI/ML research project, deciding what to investigate next, choosing datasets…

Sivasuthan9/ai-research-skill · 153 tokens

xie-saining-research-taste

Use when evaluating AI/ML research ideas, choosing research directions, framing problems, planning experiments, improving research taste or paper storytelling, resisting trend-following, or applying Saining Xie's interview-derived views on visual intelligence, world models, research culture, and scientific taste.

ky-ji/xie-saining-research-taste-skills · 63 tokens

hugging-face-paper-publisher

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

patchy631/ai-engineering-hub · 42 tokens

citation-audit

A verification tool for checking whether a paper's bibliography entries are real, correctly described, and used to support the claims they accompany.

wanshuiyin/Auto-claude-code-research-in-sleep · 86 tokens

paper-illustration

A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.

wanshuiyin/Auto-claude-code-research-in-sleep · 67 tokens

research-refine

A research-planning guide that turns a broad research idea into a specific method and a small validation plan.

wanshuiyin/Auto-claude-code-research-in-sleep · 101 tokens