claude-code-blueprint: Instructions file for Claude Code

CLAUDE.md

claude-code-blueprint CLAUDE.md is an instructions file for Claude Code from faizkhairi/claude-code-blueprint. It costs 3,009 tokens per session, scanned A, original, MIT.

A set of instructions for Claude Code that requires checking work after completing an implementation or plan.

In plain words
What is it for?
Use it to choose suitable checks for code, APIs, deployments, configuration, dependencies, Git operations, and file edits.
Why use it?
It helps catch unfinished or disconnected changes instead of treating an edit as correct merely because it was made.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is faizkhairi/claude-code-blueprint's own configuration. It tells Claude Code how to work on claude-code-blueprint 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 claude-code-blueprint configures →

Reuse

Borrowing it

Nothing to install: this file belongs to faizkhairi/claude-code-blueprint. 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/faizkhairi/claude-code-blueprint/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/faizkhairi/claude-code-blueprint

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 claude-code-blueprint CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/faizkhairi/claude-code-blueprint/claude-md.svg)](https://agentmods.dev/instructions/faizkhairi/claude-code-blueprint/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/faizkhairi/claude-code-blueprint/claude-md"><img src="https://agentmods.dev/badge/instructions/faizkhairi/claude-code-blueprint/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,009 This file is loaded in full into every session.
When invoked 3,009 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.03009 $0.03009
Opus 5 $0.01504 $0.01504
Sonnet 5 $0.00602 $0.00602
Haiku 4.5 $0.00301 $0.00301

Measured 8d ago against content hash c6bf452edb13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude-code-blueprint CLAUDE.md scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| API / server route | curl or fetch the live endpoint, check the response is real data. **Then also run the `Wiring (new symbol)` row**: a route can answer curl while being registered only in a test harness, never in th
CLAUDE.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Global Claude Behavior Rules

Verify-After-Complete (MANDATORY)

After finishing any implementation, task, or plan, ALWAYS run a verification step before declaring it done. This is non-negotiable.

Skip-excuse: "the edit obviously landed." Obvious is the feeling, not the check.

What to verify depends on what was built:

Work Type Verification Steps
Code / feature Run tests, run type check, run build. Then also run the Wiring (new symbol) row: green tests prove the code works, not that anything reaches it.
API / server route curl or fetch the live endpoint, check the response is real data. Then also run the Wiring (new symbol) row: a route can answer curl while being registered only in a test harness, never in the production router.
Deployment Hit the production URL, confirm it's not the fallback/empty state
Config change Confirm the config was actually picked up (e.g. env vars, settings)
Dependency change Confirm the install succeeded and nothing broke
Git operation git status to confirm clean state; git log to confirm commit is correct
File edit Re-read the file after editing to confirm the change landed correctly
Fact/data update Search for the NEW value (confirm present) AND search for the OLD value (confirm absent everywhere). Stale copies in other locations are the #1 missed verification.
Wiring (new symbol) Always ADDITIONAL to whichever row above matched; never a substitute for it, and never sufficient alone. Verify goal-backward: the symbol EXISTS -> is not a STUB/TODO -> something IMPORTS/REGISTERS/CALLS it -> data FLOWS end-to-end. Zero call sites = dead code: wire it now, or mark it deferred with a tracking item. Same principle as "An agent you never invoke is dead weight", applied to code.

Verification mindset

  • Don't assume it worked: run the check. A passing build does not mean correct behavior.
  • Check the actual output, not just exit codes. A 200 response returning { weeks: [], totalContributions: 0 } is not the same as a successful response with real data.
  • When something looks suspiciously perfect (zero errors, empty state "as expected"), investigate whether it's working correctly or silently failing gracefully.
  • End-to-end over unit: the most important check is always the final output the user would see, not intermediate steps.
  • Bidirectional fact checks: when updating a value (test count, version, date), grep for the OLD value across the entire scope. A fact that appears in 2 places but is only updated in 1 is a silent inconsistency.

Read the full file on GitHub · 179 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. 8d ago First seen · 179 lines · 3,009 tokens per session scan A c6bf452edb13

Subscribe to this mod's changes

claude-code-blueprint CLAUDE.md is an instructions file published in the GitHub repository faizkhairi/claude-code-blueprint (70 stars, last pushed 26d ago), licensed MIT. It adds 3,009 tokens to every session, about $0.0150 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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