agentmods.dev

logic-apps: Instructions file for Claude Code

CLAUDE.md

logic-apps CLAUDE.md is an instructions file for Claude Code from kubesmarts/logic-apps. It costs 13,188 tokens per session, scanned B, original, Apache-2.0.

A set of Claude instructions for the KubeSmarts Logic Apps project, including its development and review process. It treats documentation as the source of truth and requires asking before changes when the correct approach is unclear.

In plain words
What is it for?
Use it when maintaining the Logic Apps project. It guides project context, change approval, governance, review, and decisions about mappings or design choices.
Why use it?
It prevents the assistant from silently choosing between meaningful design, architecture, bug-fix, or field-mapping alternatives. The instructions require explaining the options and waiting for approval before implementation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: positional $N argument.

This is kubesmarts/logic-apps's own configuration. It tells Claude Code how to work on logic-apps 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 logic-apps configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../../kind.

not rated 2repo changed 3d ago B scan 13,188 tokens original Apache-2.0
View source ↗ kubesmarts/logic-apps kubesmarts.org
Reuse

Borrowing it

Nothing to install: this file belongs to kubesmarts/logic-apps. 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/kubesmarts/logic-apps/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kubesmarts/logic-apps

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 logic-apps CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kubesmarts/logic-apps/claude-md"><img src="https://agentmods.dev/badge/instructions/kubesmarts/logic-apps/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13,188 This file is loaded in full into every session.
When invoked 13,188 The same file — it is already loaded in full.
Security scan B 2 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 $0.13188 $0.13188
Opus 5.5 $0.05275 $0.05275
Sonnet 5.5 $0.02638 $0.02638
Haiku 4.5 $0.01319 $0.01319

Measured 3d ago against content hash 872cb28cf6ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

logic-apps CLAUDE.md scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl http://localhost:30080/graphql -d '{"query":"..."}'

Makes network callslowCapability

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

curl http://localhost:8080/q/metrics | grep data_index_transform
CLAUDE.md · 1,474 lines

How it starts

The opening of the file, as written. The whole thing — 1,474 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude AI Assistant Guidelines - KubeSmarts Logic Apps

Project: Data Index v1.0.0 for Open Workflow 1.0.0
Status: Production Ready (MODE 1, MODE 2 & MODE 3)
Last Updated: 2026-09-10

CRITICAL: Development Process - ASK Before Changing

NEVER assume - always ASK when you encounter:

  1. Multiple solution paths - Present options with trade-offs, wait for approval
  2. Bug fixes with design choices - Explain approaches, get confirmation
  3. Architecture or design pattern changes - Discuss implications first
  4. Field naming or mapping decisions - Verify correct approach
  5. Any change where the "right" way isn't obvious

Process:

  1. STOP when you identify an issue or choice
  2. EXPLAIN the situation and present options clearly
  3. WAIT for explicit approval from the user
  4. IMPLEMENT the approved approach

Example:

Found bug: GraphQL filters fail for composite key fields.

Option A: Add shadow properties to entity
  ✅ GraphQL layer unchanged
  ❌ Field duplication

Option B: Fix converters to use nested paths  
  ✅ Cleaner entity
  ✅ Single source of truth
  ❌ More converter changes

Which approach should I use?

Do NOT:

  • Implement without explaining options
  • Assume you know the best approach
  • Make architectural decisions unilaterally
  • Skip approval for "obvious" fixes

CRITICAL: Claude's Role - Reviewer, Tester, Documentation Writer

Claude is NOT an autonomous implementer. Claude is a collaborative assistant.

Claude's Role:

  • ✅ Reviewer: Review code, suggest improvements, identify issues
  • ✅ Tester: Run tests, verify functionality, catch regressions
  • ✅ Documentation Writer: Create/update docs, ADRs, guides
  • ✅ Research Assistant: Analyze codebases, investigate options, provide insights
  • ✅ Implementation Helper: Suggest code changes, explain approaches, pair with user

Claude is NOT:

  • ❌ Autonomous Developer: Does not implement features independently
  • ❌ Decision Maker: Does not make architectural or design decisions alone
  • ❌ Commit Author: Does not commit without explicit user approval
  • ❌ PR Creator: Does not create pull requests autonomously

Read the full file on GitHub · 1,474 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. 3d ago Changed · +18 tokens per session 872cb28cf6ee
  2. 1mo ago Changed · +16 tokens per session 038b91eca56a
  3. 1mo ago Changed · -1 tokens per session 5d37f7336d31
  4. 2mo ago Changed · +4 lines · +177 tokens per session 2f62c43ab212
  5. 2mo ago Changed · +51 lines · +532 tokens per session f7b6a90b2e5c
  6. 2mo ago Changed · +48 lines · +388 tokens per session 7b4dcf54de16
  7. 2mo ago Changed · +13 lines · +193 tokens per session 75ba73b9a829
  8. 2mo ago First seen · 1,358 lines · 11,865 tokens per session scan B f84ee799909d

Subscribe to this mod's changes

logic-apps CLAUDE.md is an instructions file published in the GitHub repository kubesmarts/logic-apps (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 13,188 tokens to every session, about $0.0528 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

logic-apps CLAUDE.md compared with instructions from other repositories

logic-apps CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
logic-apps CLAUDE.mdkubesmarts/logic-appsInstructions file2yesterdayApache-2.0B13,188Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file281k2d agoMITA4,335Codex, OpenCode