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.
npx agentmods add instructions/kubesmarts/logic-apps/claude-mdgit clone --depth 1 https://github.com/kubesmarts/logic-appsWrote 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.
[](https://agentmods.dev/instructions/kubesmarts/logic-apps/claude-md)<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="Measured on agentmods" height="20"></a>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 | $0.12058 | $0.12058 |
| Opus 5 | $0.06029 | $0.06029 |
| Sonnet 5 | $0.02412 | $0.02412 |
| Haiku 4.5 | $0.01206 | $0.01206 |
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 today.
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 How it starts
The opening of the file, as written. The whole thing — 1,371 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: 2026-08-26
CRITICAL: Development Process - ASK Before Changing
NEVER assume - always ASK when you encounter:
- Multiple solution paths - Present options with trade-offs, wait for approval
- Bug fixes with design choices - Explain approaches, get confirmation
- Architecture or design pattern changes - Discuss implications first
- Field naming or mapping decisions - Verify correct approach
- Any change where the "right" way isn't obvious
Process:
- STOP when you identify an issue or choice
- EXPLAIN the situation and present options clearly
- WAIT for explicit approval from the user
- 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: Governance and Review Process
NEVER push code or create PRs without explicit user approval:
- Test First: Always run relevant tests before committing
- Commit Locally: Commit changes to local branch only
- Report Results: Show test results and summary of changes
- Wait for Approval: User reviews and decides when to push/create PR
- No Assumptions: Don't assume code is ready just because it compiles
This is NOT negotiable. Pushing untested code or creating PRs without approval is a critical error.
CRITICAL: Documentation is the Source of Truth
ALWAYS consult and update documentation when making 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.
- today Changed · +13 lines · +193 tokens per session 75ba73b9a829
- 4d ago First seen · 1,358 lines · 11,865 tokens per session scan B f84ee799909d
logic-apps CLAUDE.md is an instructions file published in the GitHub repository kubesmarts/logic-apps (2 stars, last pushed today), licensed Apache-2.0. It adds 12,058 tokens to every session, about $0.0603 per session on Opus 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.
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.