What is skills-driven-development CLAUDE.md?

Repository instructions for Skills-Driven Development, including the active project plan, coding rules, testing commands, and requirements for writing skills. A monorepo or multi-part project may use such instructions to keep work consistent across its tools.

Use them when working on the specified SkDD project, especially for CLI changes, tests, formatting, commits, and skill validation.

They give coding agents the repository's required workflow and guardrails, reducing the chance of using the wrong package manager, test command, format, or skill structure.

How zakelfassi/skills-driven-development configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zakelfassi/skills-driven-development. 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/zakelfassi/skills-driven-development/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/zakelfassi/skills-driven-development

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zakelfassi/skills-driven-development/claude-md/github.svg)](https://agentmods.dev/instructions/zakelfassi/skills-driven-development/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/zakelfassi/skills-driven-development/claude-md"><img src="https://agentmods.dev/badge/instructions/zakelfassi/skills-driven-development/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/zakelfassi/skills-driven-development/claude-md"><img src="https://agentmods.dev/badge/instructions/zakelfassi/skills-driven-development/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 500 This file is loaded in full into every session.

When invoked 500 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.

Model	Per session	Once invoked
Fable 5.1	$0.00500	$0.00500
Opus 5.5	$0.00200	$0.00200
Sonnet 5.5	$0.00100	$0.00100
Haiku 4.5	$0.00050	$0.00050

Measured 2mo ago against content hash 48f9214cee9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skills-driven-development 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 · 24 lines

What it actually says

SkDD — agent instructions

Active goal

The current build goal is docs/plans/2026-07-skdd-commons.md — SkDD Commons + the July 2026 Frontier drop + CLI add/push + plugin hooks. If you were spun up in this repo without a more specific task, that plan is your task: read it fully, ingest its §1 context list, and execute phase by phase. Check off acceptance boxes and append to its §9 execution log as you go.

House rules

pnpm only. Node ≥20.
Tests: vitest — pnpm --dir cli test. Every new CLI command gets tests in cli/test/ mirroring the existing style (fixtures under cli/test/fixtures/).
Lint/format: biome — pnpm --dir cli lint / format. No eslint/prettier here.
Commits: conventional commits (feat:, fix:, docs:, chore: …). release-please builds CHANGELOG.md from them — never hand-edit the changelog.
The CLI is published as @zakelfassi/skdd (npm, cli/ package). Don't break existing command flags; additive changes only unless a major is planned.
Skills are spec-bound: every SKILL.md must pass skdd validate --strict (agentskills.io spec + SkDD lifecycle metadata). Author skills per skillforge/SKILL.md.

Non-goals (binding, from ROADMAP.md)

No hosted registry or server-side skill index (git is the registry). No skill-executing runtime. No review gate on forging (reviewing community imports is different and fine). No semantic search.

Operational guardrails

Harness mirror dirs (~/.claude/skills, ~/.codex/skills, …) are often populated regular directories holding skills that live in no colony. Never skdd link --force over them — it replaces the directory with a symlink and effectively deletes those skills. Mirror logic must stay non-destructive by default.
~/.skdd/ on this machine is the maintainer's live global colony, not a test fixture. Use scratch dirs for tests.

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.

2mo ago First seen · 24 lines · 500 tokens per session scan A 48f9214cee9b

Subscribe to this mod's changes

skills-driven-development CLAUDE.md is an instructions file published in the GitHub repository zakelfassi/skills-driven-development (18 stars, last pushed 3mo ago), licensed MIT. It adds 500 tokens to every session, about $0.0020 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 2026-08-30.

Building agents Planning agent-skills agentic-development ai ai-agents developer-tools skills

skills-driven-development CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skills-driven-development CLAUDE.mdzakelfassi/skills-driven-development	Instructions file	18	3mo ago	MIT	A	500	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

skills-driven-development: Instructions file for Claude Code