claude-skills: Instructions file for Claude Code

CLAUDE.md

claude-skills CLAUDE.md is an instructions file for Claude Code from oaustegard/claude-skills. It costs 4,775 tokens per session, scanned B, original, MIT.

A set of project instructions for Claude Code covering image generation, shared memory, web development, and branch and pull-request work.

In plain words
What is it for?
Use it when Claude Code works on web projects, creates visual artwork, needs persistent project context, or manages development branches and pull requests.
Why use it?
It gives the coding agent project-specific rules, such as using Gemini for generated images and starting the shared memory system automatically.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is oaustegard/claude-skills's own configuration. It tells Claude Code how to work on claude-skills 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 claude-skills configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/claude-skills/remembering.

Reuse

Borrowing it

Nothing to install: this file belongs to oaustegard/claude-skills. 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/oaustegard/claude-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/oaustegard/claude-skills

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 claude-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oaustegard/claude-skills/claude-md/github.svg)](https://agentmods.dev/instructions/oaustegard/claude-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/oaustegard/claude-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/oaustegard/claude-skills/claude-md/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.

agentmods 80×15 button for claude-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/oaustegard/claude-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/oaustegard/claude-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,775 This file is loaded in full into every session.
When invoked 4,775 The same file — it is already loaded in full.
Security scan B 2 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 $0.04775 $0.04775
Opus 5 $0.02388 $0.02388
Sonnet 5 $0.00955 $0.00955
Haiku 4.5 $0.00477 $0.00477

Measured 10d ago against content hash afe5629bfb7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

claude-skills CLAUDE.md scanned grade B with 2 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 10d 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls -la .claude/skills/skill-name 2>/dev/null

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

NOTE: `gh` IS available and authenticated via `$GH_TOKEN` in Claude Code on the web — use it for PRs (`gh pr create`). The raw GitHub API over curl works too as a fallback.
CLAUDE.md · 520 lines

How it starts

The opening of the file, as written. The whole thing — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@AGENTS.md

⚠️ Image & Art Generation: Use Gemini, Not SVG

When the task involves generating images, portraits, illustrations, or any visual art:

ALWAYS delegate to Gemini via the invoking-gemini skill. Do NOT attempt SVG or HTML canvas art.

import sys
sys.path.append('/mnt/skills/user/invoking-gemini/scripts')
from gemini_client import generate_image

result = generate_image("Your detailed prompt here", model="nano-banana-2",
                        output_path="/mnt/user-data/outputs/image.png")
  • nano-banana-2 (gemini-3.1-flash-image-preview) — default, fast
  • nano-banana-pro (gemini-3-pro-image-preview) — high fidelity, text rendering

Gemini produces actual pixel images. SVG stick figures are not a substitute.

Muninn Boot

This repository is developed by two wings of the same raven. Claude Code implements; Claude.ai (Muninn) plans, tests, and operates the memory system. Both share a persistent memory store — boot it to maintain continuity.

Boot is automatic. The SessionStart hook (.claude/hooks/session-start.sh) runs boot() at the beginning of every Claude Code on the web session. No manual invocation needed.

Credentials auto-detect from environment or well-known paths (/mnt/project/turso.env, /mnt/project/muninn.env, ~/.muninn/.env). If boot fails on missing credentials, the hook logs a warning to stderr and continues — not all sessions require memory access.

For local Claude Code sessions (not on the web), boot can be invoked manually if needed:

python3 << 'EOF'
import sys
sys.path.insert(0, '/home/user/claude-skills/remembering')
from scripts import boot
print(boot())
EOF

Decision Traces

After completing meaningful work (implementation, bugfix, architecture decision), store a memory. This is how the other wing learns what happened.

remember(
    "Closed #NNN: [what was learned]. Key decision: [rationale]. "
    "Constraint: [if any]. Future note: [what next session needs to know].",
    "decision",
    tags=["issue-NNN", "relevant-tags"],
    priority=1  # 1=significant, 0=routine
)

Read the full file on GitHub · 520 lines

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. 10d ago First seen · 520 lines · 4,775 tokens per session scan B afe5629bfb7d

Subscribe to this mod's changes

claude-skills CLAUDE.md is an instructions file published in the GitHub repository oaustegard/claude-skills (148 stars, last pushed today), licensed MIT. It adds 4,775 tokens to every session, about $0.0239 per session on Opus 5. A static security scan graded it B with 2 findings (enumerates other installed skills, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens