slop-guard: Skill for Claude Code

.claude/skills/qa/SKILL.md

qa is a skill for Claude Code from eric-tramel/slop-guard. It costs 37 tokens per session (2,342 once invoked), scanned A, original, MIT.

A black-box quality audit skill for Slop-Guard, checking the product through its public interfaces without reading its source code or tests.

In plain words
What is it for?
Use it to test Slop-Guard through its MCP tools or command-line interface and create GitHub issues for confirmed problems.
Why use it?
It helps find real problems in the tool, its command-line interface, documentation, agent workflows, and writing results while avoiding duplicate reports.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

This is eric-tramel/slop-guard's own configuration. It tells Claude Code how to work on slop-guard 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 slop-guard configures →

Reuse

Borrowing it

Nothing to install: this file belongs to eric-tramel/slop-guard. 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/eric-tramel/slop-guard/main/.claude/skills/qa/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/eric-tramel/slop-guard

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 qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/eric-tramel/slop-guard/qa.svg)](https://agentmods.dev/skills/eric-tramel/slop-guard/qa)
Your own site
<a href="https://agentmods.dev/skills/eric-tramel/slop-guard/qa"><img src="https://agentmods.dev/badge/skills/eric-tramel/slop-guard/qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,342 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00037 $0.02342
Opus 5 $0.00018 $0.01171
Sonnet 5 $0.00007 $0.00468
Haiku 4.5 $0.00004 $0.00234

Measured 6d ago against content hash ecf9b859df1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qa 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.

.claude/skills/qa/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slop-Guard QA Audit

Black-box QA of slop-guard through its public interfaces only. Do not read source files or tests to find bugs — discover issues by using the product as an agent or user would.

Launch parallel subagents per testing angle. File genuine issues with gh issue create. If $ARGUMENTS specifies a focus area (mcp, cli, fit, docs, workflows, or effectiveness), run only that angle. Otherwise run all 6 in parallel.

Setup

  1. Read README.md for documented behavior.
  2. If mcp__slop_guard__* tools are available, fetch their schemas via tool search.
  3. Fetch open issues to avoid duplicates:
    gh issue list --repo eric-tramel/slop-guard --limit 100 --state open --json number,title,body,labels
    
  4. Prefer local QA fixtures if present. Otherwise create temp files under /tmp/slop-guard-qa. Do not write throwaway files into the repo.

Pass the open issues list into every subagent prompt.

Testing Angles

1. MCP Agent Interface (mcp)

Is the MCP surface clear, consistent, and useful for an agent?

  • Tool descriptions, parameter clarity, distinction between check_slop and check_slop_file
  • JSON output structure: score, band, violations, counts, advice, file
  • Edge cases: short text, empty strings, unicode, markdown, code fences, long inputs
  • Missing/unreadable file paths
  • Response size and parseability
  • Cross-check MCP vs CLI JSON output on the same input

Issue prefix: mcp:

2. CLI UX (cli)

Does uv run sg behave predictably?

  • All flags from sg --help: --json, --verbose, --quiet, --threshold, --score-only, --counts, --config, --version
  • Input modes: file paths, inline text, stdin (-), multiple inputs
  • Exit codes: 0 (pass), 1 (threshold fail), 2 (error)
  • Stdout/stderr separation for scripting
  • Path-vs-inline-text ambiguity
  • Missing files, bad config paths

Issue prefix: cli:

3. Fit Workflow (fit)

Can a user fit a custom rule config from docs alone?

Read the full file on GitHub · 184 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 · 184 lines · 37 tokens per session scan A ecf9b859df1b

Subscribe to this mod's changes

qa is a skill published in the GitHub repository eric-tramel/slop-guard (163 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 2,342 once invoked, about $0.0002 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 2026-08-30.