agentmods.dev

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.

In plain words
What is it for?
Use them when working on the specified SkDD project, especially for CLI changes, tests, formatting, commits, and skill validation.
Why use it?
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.

Instructions file

18 1mo ago A scan 500 tokens original MIT
View the source file zakelfassi/skills-driven-development
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/zakelfassi/skills-driven-development/claude-md
Clone the repo
git clone --depth 1 https://github.com/zakelfassi/skills-driven-development
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. Scan, not verified.
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 $0.00500 $0.00500
Opus 5 $0.00250 $0.00250
Sonnet 5 $0.00100 $0.00100
Haiku 4.5 $0.00050 $0.00050

Measured 3d ago against content hash 48f9214cee9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

  1. 3d 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 1mo ago), licensed MIT. It adds 500 tokens to every session, about $0.0025 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 2026-08-30.

Building agentsPlanningagent-skillsagentic-developmentaiai-agentsdeveloper-toolsskills
Related

Other instructions, from other repositories

cortex-mem AGENTS.md

Instructions for sopaco/cortex-mem, covering cortex memory - ai agent context guide, project overview, core concepts, memory dimensions and three-tier layers.

sopaco/cortex-mem · 1,620 tokens

ai-toolkit AGENTS.md

Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).

pipefy/ai-toolkit · 3,184 tokens

superpowers-reasonix AGENTS.md

Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.

christopherarter/superpowers-reasonix · 761 tokens

ai-mind AGENTS.md

Instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.

HWYD/ai-mind · 3,170 tokens

agent-skills AGENTS.md

Instructions for sayeed1999/agent-skills, covering agents.md, output style, output style, 1. think before code and 2. simplicity.

sayeed1999/agent-skills · 1,146 tokens

webflow-skills AGENTS.md

Instructions for 224-Industries/webflow-skills, covering 224 industries - webflow agent skills repository, agents.md (symlink to claude.md), repo structure, reference file conventions and content style.

224-Industries/webflow-skills · 911 tokens