agentmods.dev

Agentic-development: Instructions file for Claude Code

CLAUDE.md

Agentic-development CLAUDE.md is an instructions file for Claude Code from MatrixFounder/Agentic-development. It costs 3,700 tokens per session, scanned A, original, Apache-2.0.

A project instruction file for Claude Code that defines an automated development workflow, reusable skills, session restoration, and tool-execution rules. Claude Code is a coding assistant that follows project instructions while working on software.

In plain words
What is it for?
It configures session bootstrap, skill loading, workflow execution, and phase-boundary state updates. It supports projects that coordinate development through agent instructions.
Why use it?
It gives the assistant a consistent process for starting tasks and restoring unfinished work. It also tells the assistant where authoritative project instructions live.

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 MatrixFounder/Agentic-development's own configuration. It tells Claude Code how to work on Agentic-development 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 Agentic-development configures →

not rated 6repo changed yesterday A scan 3,700 tokens original Apache-2.0
View source ↗ MatrixFounder/Agentic-development
Reuse

Borrowing it

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

agentmods badge for Agentic-development CLAUDE.md

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

agentmods 80×15 button for Agentic-development CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/matrixfounder/agentic-development/claude-md"><img src="https://agentmods.dev/badge/instructions/matrixfounder/agentic-development/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,700 This file is loaded in full into every session.
When invoked 3,700 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 $0.03700 $0.03700
Opus 5.5 $0.01480 $0.01480
Sonnet 5.5 $0.00740 $0.00740
Haiku 4.5 $0.00370 $0.00370

Measured yesterday against content hash 44ef82207148, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Agentic-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 yesterday.

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 · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent_prompt.md - AUTOMATED ORCHESTRATION MODE

You are the Orchestrator Agent powering this IDE. Your Source of Truth is the folder /System/Agents (root prompts) and the docs/ folder.

CRITICAL INSTRUCTION

When the user gives you a task, you must NOT just write code immediately. You must execute the Agentic Pipeline defined below.

SKILLS SYSTEM ARCHITECTURE

The system relies on a modular Skills System:

  1. Definitions: Located in .agent/skills/[skill-name]/SKILL.md. These are the source of truth.
  2. Usage: Agents declare "Active Skills" in their prompts. You MUST read these skill files when assuming an agent role.

SESSION RESTORATION (BOOTSTRAP)

ON SESSION START:

  1. Read .agent/sessions/latest.yaml using the Read tool.
  2. IF EXISTS and contains valid state: Announce restored context to the user: "Restored session: Mode=[mode], Task=[task_name], Status=[status]."
  3. IF NOT EXISTS or empty: Proceed with new task analysis.
  4. CONFLICT RESOLUTION: User's current request always takes precedence over restored state.
  5. DISAGREEMENT CHECK: If the state was restored and docs/TASK.md exists, read its H1 and its Task ID.
    • Both it and current_task.name carry a task ID, and the IDs differ: add to the announcement "Session state and docs/TASK.md disagree: latest.yaml names [ID], docs/TASK.md is [ID]." The user's request decides which task continues; when it does not, ask the operator.
    • Either carries no task ID: name the H1 of docs/TASK.md beside the restored task, and ask nothing.
    • The IDs are equal: nothing changes.

ON PHASE BOUNDARY (after completing each pipeline stage):

  1. Run via Bash: python3 .agent/skills/skill-session-state/scripts/update_state.py --mode "[Mode]" --task "[TaskName]" --status "[Status]" --summary "[Summary]"
  2. This persists context for session recovery.
  3. If update_state.py exits non-zero, tell the operator in the same reply: the command, the exit code and the last line of its output. Do not write .agent/sessions/latest.yaml by hand in place of the run. Continue the task; a workflow's own stop rules still apply.

Read the full file on GitHub · 162 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. yesterday Changed · +6 lines · +205 tokens per session 44ef82207148
  2. 11d ago Changed · +4 lines · +169 tokens per session 7018b09f6fc5
  3. 24d ago Changed · +4 lines · +143 tokens per session 13de1a8655f4
  4. 1mo ago Changed · +1 lines · +401 tokens per session 1ff2e74233f9
  5. 1mo ago First seen · 147 lines · 2,782 tokens per session scan A 327040f12ada

Subscribe to this mod's changes

Agentic-development CLAUDE.md is an instructions file published in the GitHub repository MatrixFounder/Agentic-development (6 stars, last pushed today), licensed Apache-2.0. It adds 3,700 tokens to every session, about $0.0148 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 2026-09-03.

Building agentsClaude CodeProject managementTDDagenticai-agentsvdd
Related

Other instructions, from other repositories

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 · 9,715 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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

vscode model-prompts.instructions.md

Model-specific prompt authoring and registry guidelines.

microsoft/vscode · 2,022 tokens