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.
curl -O https://raw.githubusercontent.com/eric-tramel/slop-guard/main/.claude/skills/qa/SKILL.mdgit clone --depth 1 https://github.com/eric-tramel/slop-guardWrote 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/skills/eric-tramel/slop-guard/qa)<a href="https://agentmods.dev/skills/eric-tramel/slop-guard/qa"><img src="https://agentmods.dev/badge/skills/eric-tramel/slop-guard/qa/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 70 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00037 | $0.02342 |
| Opus 5.5 | $0.00015 | $0.00937 |
| Sonnet 5.5 | $0.00007 | $0.00468 |
| Haiku 4.5 | $0.00004 | $0.00234 |
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 2mo 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.
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
- Read
README.mdfor documented behavior. - If
mcp__slop_guard__*tools are available, fetch their schemas via tool search. - Fetch open issues to avoid duplicates:
gh issue list --repo eric-tramel/slop-guard --limit 100 --state open --json number,title,body,labels - 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_slopandcheck_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?
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.
- 2mo ago First seen · 184 lines · 37 tokens per session scan A ecf9b859df1b
qa is a skill published in the GitHub repository eric-tramel/slop-guard (167 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 2,342 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…
mantis-reproduce
Generates and runs crash reproducers to verify security flaws. Use when viable findings exist and you need to write and execute a script or payload to verify the crash. Don't use for code auditing or patching.