skilldeck: Instructions file for Claude Code

CLAUDE.md

skilldeck CLAUDE.md is an instructions file for Claude Code from aliaihub/skilldeck. It costs 3,753 tokens per session, scanned A, original, MIT.

A project guide for Skilldeck, a desktop app that manages AI-agent instruction files such as SKILL.md, CLAUDE.md, and AGENTS.md across projects and tools.

In plain words
What is it for?
Use it when developing Skilldeck, choosing the next incomplete feature, following its one-feature-at-a-time workflow, or running its required checks.
Why use it?
It gives agents the project context and required verification process, helping keep changes focused and ensuring each feature is tested before moving on.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

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

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/ali/.skilldeck/library.

Reuse

Borrowing it

Nothing to install: this file belongs to aliaihub/skilldeck. 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/aliaihub/skilldeck/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/aliaihub/skilldeck

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 skilldeck CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aliaihub/skilldeck/claude-md"><img src="https://agentmods.dev/badge/instructions/aliaihub/skilldeck/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,753 This file is loaded in full into every session.
When invoked 3,753 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.03753 $0.03753
Opus 5.5 $0.01501 $0.01501
Sonnet 5.5 $0.00751 $0.00751
Haiku 4.5 $0.00375 $0.00375

Measured 2mo ago against content hash f93395e59e4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skilldeck CLAUDE.md scanned grade A with 1 finding 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 2mo 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **CLI integration:** Node.js child_process (for Playground feature — Phase 2)
CLAUDE.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skilldeck — Agent Project Bible

What This Project Is

Skilldeck is a desktop application for managing AI agent skill files (SKILL.md, CLAUDE.md, AGENTS.md) across projects and tools. It solves three problems:

  1. Scatter — skill files live in different places, copies diverge, starting a new project means rebuilding behavioral infrastructure from scratch
  2. Opacity — no way to know which skills are active in a project, at what version, or whether they've drifted
  3. No verification — no feedback mechanism to know if a skill file is actually changing agent behavior

Skilldeck is also a harness engineering experiment. It is being built by AI agents following harness methodology. The build process itself is the proof of concept.

Rules Every Agent Must Follow

  1. Read before touching. Before any coding session begins, read this file, claude-progress.txt, and feature_list.json. Do not skip this.

  2. One feature at a time. One feature, one commit. Pick the highest-priority incomplete feature from feature_list.json. Complete it. Run the full verification sequence below. Commit. Then move to the next feature.

    Full verification sequence — every step must pass before committing:

    # Step 1 — feature test (must pass first)
    npx playwright test verify.spec.ts --grep F00X
    
    # Step 2 — invariant checks (always-true system properties)
    node check-invariants.js --always
    
    # Step 3 — regression gate (re-run affected passing tests)
    REGRESSION=$(node get-regression-tests.js F00X)
    npx playwright test verify.spec.ts --grep "$REGRESSION"
    
    # Step 4 — only if all three pass: mark passing, commit
    node -e "const fs=require('fs');const f=JSON.parse(fs.readFileSync('feature_list.json','utf8'));const x=f.features.find(x=>x.id==='F00X');x.passes=true;x.notes='Verified with Playwright + invariants + regression gate';fs.writeFileSync('feature_list.json',JSON.stringify(f,null,2));"
    git add .
    git commit -m "feat(F00X): short description of what was built"
    

Read the full file on GitHub · 295 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. 2mo ago First seen · 295 lines · 3,753 tokens per session scan A f93395e59e4e

Subscribe to this mod's changes

skilldeck CLAUDE.md is an instructions file published in the GitHub repository aliaihub/skilldeck (15 stars, last pushed 7mo ago), licensed MIT. It adds 3,753 tokens to every session, about $0.0150 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

skilldeck CLAUDE.md compared with instructions from other repositories

skilldeck CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skilldeck CLAUDE.mdaliaihub/skilldeckInstructions file157mo agoMITA3,753Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode