What is sumo-qa AGENTS.md?

Setup instructions for sumo-qa, an MCP server and installer that connects a project to supported coding-agent hosts. It also describes how to create GitHub issues using the repository's templates.

Use it to install sumo-qa, configure detected hosts such as Claude Code, and prepare correctly formatted GitHub issues for implementation work.

It explains the expected installation path and host configuration, reducing setup mistakes when adding sumo-qa to an agent environment.

How sumithr/sumo-qa configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to sumithr/sumo-qa. 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/sumithr/sumo-qa/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sumithr/sumo-qa

Made for: Claude Code, Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sumithr/sumo-qa/agents-md/github.svg)](https://agentmods.dev/instructions/sumithr/sumo-qa/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sumithr/sumo-qa/agents-md"><img src="https://agentmods.dev/badge/instructions/sumithr/sumo-qa/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sumithr/sumo-qa/agents-md"><img src="https://agentmods.dev/badge/instructions/sumithr/sumo-qa/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,597 This file is loaded in full into every session.

When invoked 1,597 The same file — it is already loaded in full.

Security scan B 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.

Model	Per session	Once invoked
Fable 5.1	$0.01597	$0.01597
Opus 5.5	$0.00639	$0.00639
Sonnet 5.5	$0.00319	$0.00319
Haiku 4.5	$0.00160	$0.00160

Measured 19d ago against content hash f225f3157692, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

sumo-qa AGENTS.md scanned grade B 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 19d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| Run the verification call | Anything that requires admin / sudo elevation |

AGENTS.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md, sumo-qa setup

If you're an AI agent setting up sumo-qa for the user, follow this exactly. One command for the common case; per-host flags if you only need to wire one host.

GitHub issue creation

When creating GitHub issues, use the closest template in .github/ISSUE_TEMPLATE/ and include every required field in the issue body. For implementation tasks raised by an AI agent, use .github/ISSUE_TEMPLATE/ai-task.yml unless a more specific template fits better.

Default: configure every detected host

python -m pip install sumo-qa
python -m sumo_qa.installer

pip install sumo-qa creates both sumo-qa (the MCP server binary) and sumo-qa-install (this configurator). Use python -m sumo_qa.installer for setup because it works even when the pip Scripts directory is not on PATH yet.

What sumo-qa-install does:

Locates the sumo-qa MCP binary. If pip install sumo-qa already put it on PATH (the common case), uses that path directly: no uv invocation. If sumo-qa is not on PATH yet, falls back to uv tool install and prints uv install instructions if uv is also missing.
Claude Code (if ~/.claude/ exists): symlinks each skills/<name>/ into ~/.claude/skills/<name>/. Writes claude_desktop_config.json with the MCP entry pointing at the absolute binary path.
VS Code + Copilot (if cwd is a workspace with .git / .vscode / package.json / etc.): writes .vscode/mcp.json with the VS Code-native schema (servers key, type: stdio).
JetBrains IDEs (if JetBrains config dir exists): prints exact Settings UI steps. JetBrains' MCP plugin requires Settings UI registration: external XML writes don't reliably register the runtime coroutine.
Verifies the binary responds to JSON-RPC initialize.

Per-host flags

Use these when you only want to configure one host:

python -m sumo_qa.installer --claude-code              # Claude Code only
python -m sumo_qa.installer --vscode                   # VS Code workspace (cwd-based)
python -m sumo_qa.installer --vscode --workspace /path/to/repo
python -m sumo_qa.installer --jetbrains                # Prints JetBrains UI steps only
python -m sumo_qa.installer --vscode --skip-mcp-install   # Skip uv reinstall for speed
python -m sumo_qa.installer --profile core             # Save the MCP tool profile, then configure every detected host
python -m sumo_qa.installer --profile core --vscode    # Save the profile, then configure VS Code only

Read the full file on GitHub · 121 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.

19d ago Changed · +2 lines · +53 tokens per session f225f3157692
22d ago Changed · +4 lines · +111 tokens per session a63ca529b1c7
1mo ago First seen · 115 lines · 1,433 tokens per session scan B 66e3571af69b

Subscribe to this mod's changes

sumo-qa AGENTS.md is an instructions file published in the GitHub repository sumithr/sumo-qa (7 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,597 tokens to every session, about $0.0064 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Code review Testing ai-agents istqb mcp mcp-server

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

sumo-qa: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade B, and why

Asks for rootmediumPrivilege escalation

How it starts

AGENTS.md, sumo-qa setup

GitHub issue creation

Default: configure every detected host

Per-host flags

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

deepseek-harness AGENTS.md

vscode copilot-instructions.md