agentmods.dev

ac-infinity-mcp CLAUDE.md

ac-infinity-mcp CLAUDE.md is an instructions file for Claude Code from ober37/ac-infinity-mcp. It costs 4,857 tokens per session, scanned A, original, MIT.

A set of instructions for contributing to an MCP server connected to AC Infinity devices. It defines the project's issue, pull-request, testing, and review process.

In plain words
What is it for?
Use it when fixing issues or adding features in the AC Infinity MCP repository, including preparing and checking pull requests.
Why use it?
It prevents changes from bypassing the repository's required review stages or being merged before approval.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents.

not rated 5 yesterday A scan 4,857 tokens original MIT
View the source file ober37/ac-infinity-mcp ober37.github.io
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/ober37/ac-infinity-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/ober37/ac-infinity-mcp

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 ac-infinity-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ober37/ac-infinity-mcp/claude-md.svg)](https://agentmods.dev/instructions/ober37/ac-infinity-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ober37/ac-infinity-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ober37/ac-infinity-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,857 This file is loaded in full into every session.
When invoked 4,857 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 5.1 $0.04857 $0.04857
Opus 5 $0.02429 $0.02429
Sonnet 5 $0.00971 $0.00971
Haiku 4.5 $0.00486 $0.00486

Measured 6d ago against content hash 99801fe5f18a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ac-infinity-mcp 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 407 lines

How it starts

The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Contribution Protocol

This file is the authoritative source for how Claude agents contribute to this repo.

Contribution Rules

  • Never push directly to main. All work goes through feature branches + PRs.

  • Each phase = one PR. Phases are never bundled.

  • Every issue follows the 4-Stage Issue Workflow Protocol (see below).

  • No PR is raised until all four stages pass. Any stage failure restarts from Stage 1.

  • All PRs are created as drafts. Convert to "ready for review" only after Gate 5 (manual smoke test) is approved by the user. CI runs on draft PRs, so the test gate is not bypassed.

  • PRs are never merged without explicit user permission. After Gate 5 approval and all CI gates pass, present the status to the user and wait for them to say "merge" (or equivalent) before running gh pr merge.

  • Before declaring CI green or recommending merge, verify the PR's actual branch state: Run gh pr view <N> --json mergeStateStatus,mergeable,headRefOid,headRefName and confirm:

    • mergeStateStatus is CLEAN (not BEHIND, DIRTY, or CONFLICTING)
    • mergeable is MERGEABLE (not CONFLICTING)
    • headRefOid matches the local branch HEAD (git rev-parse HEAD)

    CONFLICTING on either field means a merge conflict exists — do not report CI passing and do not request merge until the conflict is resolved. Fix: abort any in-progress rebase, save the full diff (git diff origin/main HEAD > /tmp/branch.patch), reset to main (git reset --hard origin/main), re-apply (git apply /tmp/branch.patch), commit, then force-push. A PR that is BEHIND main must be similarly rebased and re-pushed before the all-clear is given. Never report CI passing from a stale run — confirm the run SHA matches the current HEAD SHA.

GitHub Issue Hygiene

Every issue must have both a label and a milestone applied before a PR is raised against it. When creating a new issue, apply both immediately. When triaging unlabeled or un-milestoned issues, audit and update before beginning work.

Read the full file on GitHub · 407 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. 6d ago First seen · 407 lines · 4,857 tokens per session scan A 99801fe5f18a

Subscribe to this mod's changes

ac-infinity-mcp CLAUDE.md is an instructions file published in the GitHub repository ober37/ac-infinity-mcp (5 stars, last pushed yesterday), licensed MIT. It adds 4,857 tokens to every session, about $0.0243 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 2026-08-31.

ac-infinityai-agentsgrowgrowtentmcpmcp-server
Related

Other instructions, from other repositories

blockrun-mcp AGENTS.md

AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.

BlockRunAI/blockrun-mcp · 282 tokens

openrouter-mcp-multimodal AGENTS.md

AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).

stabgan/openrouter-mcp-multimodal · 793 tokens

intervals-icu-mcp CLAUDE.md

Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.

hhopke/intervals-icu-mcp · 1,873 tokens

ai-toolkit AGENTS.md

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

flyto-core CLAUDE.md

Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.

flytohub/flyto-core · 367 tokens

Plonk AGENTS.md

AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.

ostapondo/Plonk · 3,557 tokens