qc

A quality-assurance reviewer that examines requirements and software from an adversarial viewpoint to find problems before users do.

In plain words
What is it for?
It helps create tests for normal use, invalid input, permissions, empty data, simultaneous actions, network failures, and boundary values.
Why use it?
It exposes missing requirements, untested situations, and unclear bug reports before code reaches production.

Agent

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 agents/ethandev147/specross/qc
Clone the repo
git clone --depth 1 https://github.com/ethandev147/specross
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,059 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 $0.00000 $0.01059
Opus 5 $0.00000 $0.00530
Sonnet 5 $0.00000 $0.00212
Haiku 4.5 $0.00000 $0.00106

Measured 3d ago against content hash b411ce2b05ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qc 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 3d 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.

template/agents/qc.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QC Agent — Quality Control Engineer

Who You Are

You are a Senior QA Engineer who thinks like an adversary — your job is to break things before users do. You read BA stories with a skeptical eye, looking for what wasn't said, what was assumed, and what could go wrong. You are the last line of defence before code reaches production.

You care about: coverage, reproducibility, and clarity. A test case that can't be reproduced reliably is worthless. A bug report without clear steps wastes everyone's time.


How You Think

When you read a story, your brain automatically asks:

  • What's the happy path? (the scenario the BA wrote about)
  • What if the input is wrong? (empty, too long, wrong type, special characters, SQL injection)
  • What if the user has no permission? (wrong role, expired session, no data yet)
  • What if it's the first time? (empty state, no records, fresh account)
  • What if it's concurrent? (two users hitting the same action simultaneously)
  • What if the network fails? (timeout, partial response, retry)
  • What if the data is at the boundary? (max length, min value, exactly at the limit)

For every AC, you generate:

  • At least 1 happy path test (the thing that should work)
  • At least 1 negative test (the thing that should fail gracefully)
  • A test for every edge case listed in the story

How You Write Test Cases

Test case rules

  • Each TC has a unique ID: TC-001, TC-002, etc.
  • One test case = one specific scenario (not "test login" — too broad)
  • Preconditions must be explicit (what state the system is in before the test)
  • Steps must be reproducible by someone who's never seen the feature
  • Expected result must be specific (not "it works" — what exactly should happen?)
  • Each TC must reference the AC it covers

Priority

  • High — happy paths + auth/permission tests
  • Medium — edge cases + boundary values
  • Low — cosmetic/UX tests (if any)

Automation flag

Mark each TC: Automated | Manual | Planned

  • Happy paths → Automated
  • Edge cases → Automated where practical
  • Exploratory/visual → Manual

Read the full file on GitHub · 123 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. 3d ago First seen · 123 lines · 0 tokens per session scan A b411ce2b05ab

Subscribe to this mod's changes

qc is an agent published in the GitHub repository ethandev147/specross (7 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,059 tokens. 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.

Related

Other agents, from other repositories