agentmods.dev

dsh-skills: Instructions file for Claude Code

CLAUDE.md

dsh-skills CLAUDE.md is an instructions file for Claude Code from arch3rPro/dsh-skills. It costs 768 tokens per session, scanned A, original, MIT.

Repository instructions for dsh-skills, a collection of coding-agent skills based on DeepSeek Harness engineering practices. They describe the folder structure, editing rules, validation tools, and release checks.

In plain words
What is it for?
Use them when adding or editing skills, documentation, agent configuration, validation scripts, or marketplace files.
Why use it?
They help contributors place skills correctly and catch invalid metadata or documentation before changes are submitted.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is arch3rPro/dsh-skills's own configuration. It tells Claude Code how to work on dsh-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 dsh-skills configures →

not rated 4repo 20d ago A scan 768 tokens original MIT
View source ↗ arch3rPro/dsh-skills
Reuse

Borrowing it

Nothing to install: this file belongs to arch3rPro/dsh-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/arch3rPro/dsh-skills/dsh-skills/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/arch3rPro/dsh-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 dsh-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arch3rpro/dsh-skills/claude-md.svg)](https://agentmods.dev/instructions/arch3rpro/dsh-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/arch3rpro/dsh-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/arch3rpro/dsh-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 768 This file is loaded in full into every session.
When invoked 768 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 $0.00768 $0.00768
Opus 5 $0.00384 $0.00384
Sonnet 5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 7d ago against content hash 0bf20fb0abee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

dsh-skills 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 7d 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 · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — dsh-skills

A set of coding-agent skills distilled from the engineering conventions of DeepSeek Harness. The project is dsh-skills (DeepSeek-Harness-Skills); the full name appears only in the README.

Repository layout

skills/<category>/<name>/SKILL.md    the executable standard (any harness)
skills/<category>/<name>/agents/openai.yaml   Codex metadata + invocation policy
docs/<category>/<name>.md           human-facing docs page per skill
reference/                          read-only upstream clones — gitignored, never edited
.claude-plugin/plugin.json          Claude Code plugin manifest
.claude-plugin/marketplace.json     Claude Code marketplace (npx skills / plugin install)
scripts/link-skills.sh              symlink every skill into ~/.claude/skills and ~/.agents/skills
scripts/validate-skills.py          strict-validate every SKILL.md + openai.yaml (run before push)
.github/workflows/validate.yml      CI gate: runs the validator on every push/PR

Categories: architecture/, testing/, documentation/, process/.

Standing orders

  • Every skill is one <category>/<name> directory carrying SKILL.md, agents/openai.yaml, and a matching docs/<category>/<name>.md page. Add all three in one change.
  • Design from adaptability, not from the conversation. Ground each skill's scope and rationale in project adaptability (when does the standard apply to a project — and when does it not?) and agent adaptability (when and how does the agent reach for it, and by what invocation).
  • Never transcribe conversation feedback into rules. User feedback, this session's discussion, and reviewer commentary about a skill are input about how to design the skill — they are never themselves rules, standards, or phrases to paste into SKILL.md, openai.yaml, or docs pages. State the resulting engineering principle on its own merits, sourced from project and agent adaptability, with no echo of who said it or when.
  • Generalize. Keep only conventions that transfer across projects; drop dsh-specific machinery (its plugin host, bilingual pairing, CI gates, vendoring). Frame an opinionated architecture choice as a conditional decision — state when it applies — never as a universal mandate.
  • Write for the agent. Call the Skill tool with "writing-for-agents" (and its SKILL-MECHANICS.md) when authoring: leading words, steps with completion criteria, positive phrasing, single source of truth, no no-ops.
  • Invocation choice. Default to model-invoked (agent reaches for it autonomously): omit disable-model-invocation, and keep interface only in agents/openai.yaml. A user-invoked skill sets disable-model-invocation: true and policy.allow_implicit_invocation: false. Keep the two files in sync — a skill is invoked the same way in every harness.
  • Keep one home per fact. State a rule in exactly one skill; link elsewhere with a relative path. Use relative links inside docs/.
  • Reference repos are read-only. Never edit or commit reference/; it exists only as extraction source material.
  • Update README.md (index + status table) and .claude-plugin/plugin.json whenever a skill is added, renamed, or removed.

Read the full file on GitHub · 36 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. 7d ago First seen · 36 lines · 768 tokens per session scan A 0bf20fb0abee

Subscribe to this mod's changes

dsh-skills CLAUDE.md is an instructions file published in the GitHub repository arch3rPro/dsh-skills (4 stars, last pushed 20d ago), licensed MIT. It adds 768 tokens to every session, about $0.0038 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 2026-08-31.

Claude Codeagent-orchestrationagent-skillsclaude-skillscodex-skilldsh
Related

Other instructions, from other repositories

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

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

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

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

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