agentmods.dev

sharedskills: Instructions file for Claude Code

CLAUDE.md

sharedskills CLAUDE.md is an instructions file for Claude Code from dmoskov/sharedskills. It costs 431 tokens per session, scanned A, original, MIT.

A collection of shared programming utilities and AI-development tools used across several projects. It includes an Asana client, Letta agent integrations, reusable agent skills, subagents, and command-line tools.

In plain words
What is it for?
Use it for Asana task and project operations, Letta agent support, task breakdown, codebase checks, cleanup, security reviews, and other shared agent workflows.
Why use it?
It avoids copying the same integrations, configuration loaders, and development workflows into every project. Shared code can be maintained in one place and reused elsewhere.

Instructions file for Claude Code

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

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

not rated 2repo changed 2mo ago A scan 431 tokens original MIT
View source ↗ dmoskov/sharedskills
Reuse

Borrowing it

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

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 sharedskills CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dmoskov/sharedskills/claude-md"><img src="https://agentmods.dev/badge/instructions/dmoskov/sharedskills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 431 This file is loaded in full into every session.
When invoked 431 The same file — it is already loaded in full.
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 $0.00431 $0.00431
Opus 5.5 $0.00172 $0.00172
Sonnet 5.5 $0.00086 $0.00086
Haiku 4.5 $0.00043 $0.00043

Measured 2mo ago against content hash b4c020d8d73d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sharedskills CLAUDE.md 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 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.

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.md · 28 lines

What it actually says

Shared Skills & Tools

Cross-project shared utilities for Dustin's AI development ecosystem.

Structure

  • asana/ — Asana client library and SDK. Used by all projects via sys.path.insert(0, "ai-dev-tools/asana").
    • asana_client.py — Unified Asana client (Secrets Manager OAuth preferred; injected tokens supported)
    • asana_config_loader.py — Workspace config (GIDs) from YAML (~/.config/ai-dev-tools/asana_config.yaml)
    • decomposition.py — Synapse-style task decomposition algorithm (stdlib-only)
    • asana_sdk/ — Full SDK: tasks, projects, custom_fields, goals, attachments, users
    • bin/asana — CLI tool
  • letta/ — Letta agent integration: hooks, session management, templates
  • skills/ — Claude Code skills (SKILL.md format)
    • asana/ — Asana CLI skill
    • task-decomposition/ — Break large tasks into file-level Asana subtasks (config-driven, no hardcoded GIDs)
    • claudemd-generator/, security-audit/, code-cleanup/ — generic codebase skills
    • rlm/ — Recursive Language Model for long-context decomposition
  • agents/ — Generic Claude Code subagent personas for .claude/agents/ (16 roles: debugger, architecture, testing, ...)
  • tools/ — Letta agent tools (installed on all agents)
    • aws_tool.py, claude_tool.py, db_query_tool.py, fetch_webpage_tool.py, semantic_search_tool.py, web_search_tool.py

Important

  • This repo is PUBLIC. Generic skills only. Project-specific code goes in project repos.
  • sharedskills/ symlink → tools/ for backward compatibility.
  • asana/ path must not change — 5+ files across repos import from it.
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 Changed · +5 tokens per session b4c020d8d73d
  2. 2mo ago First seen · 28 lines · 426 tokens per session scan A ba2e7eaf3632

Subscribe to this mod's changes

sharedskills CLAUDE.md is an instructions file published in the GitHub repository dmoskov/sharedskills (2 stars, last pushed 2d ago), licensed MIT. It adds 431 tokens to every session, about $0.0017 per session on Opus 5.5. 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 2026-08-31.

Related

sharedskills CLAUDE.md compared with instructions from other repositories

sharedskills CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sharedskills CLAUDE.mddmoskov/sharedskillsInstructions file22d agoMITA431Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file281k2d agoMITA4,335Codex, OpenCode