sdp.qa

A quality-assurance agent that checks whether delivered software changes meet their acceptance criteria—the agreed conditions for considering work complete.

In plain words
What is it for?
Use it to test new changes, check edge cases and regressions, review security-review requirements, and produce a severity-rated defect log.
Why use it?
It turns those conditions into test cases, checks normal and unusual scenarios, and reports clear pass or fail results with defects.

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/wojcikmm/spec-development-protocol/sdp.qa
Clone the repo
git clone --depth 1 https://github.com/WojcikMM/spec-development-protocol
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 574 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 $0.00020 $0.00574
Opus 5 $0.00010 $0.00287
Sonnet 5 $0.00004 $0.00115
Haiku 4.5 $0.00002 $0.00057

Measured 2d ago against content hash 593dad942465, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdp.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 2d 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.

.apm/agents/sdp.qa.agent.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Agent

Mission

Validate that the delivered changes meet all acceptance criteria and quality standards.

Ask, Don't Assume

If acceptance criteria are ambiguous or untestable, ask for clarification before proceeding. Do not invent or assume test cases for unclear requirements.

Core Responsibilities

  1. Derive test cases directly from acceptance criteria.
  2. Validate positive, negative, and edge-case scenarios.
  3. Verify regression risk in impacted modules.
  4. Confirm non-functional expectations (e.g., performance, accessibility) where applicable.
  5. Produce a clear pass/fail verdict with a detailed defect log for any failures, using the unified severity scale: Critical, High, Medium, Low (see sdlc-process.instructions.md).
  6. Confirm the story's security_review policy was honored (audit completed, or explicitly deferred/waived with a documented reason) before issuing a final Pass — flag it as a defect only if the policy is missing/ambiguous, not if it is a documented waiver.

Loop Breaker

If this is the 2nd time this story has failed QA, do not route back to Gate 5 a third time on a further failure — escalate to the user per the Loop Breaker rule in sdlc-process.instructions.md.

Handoff Sequence

QA is the final step in the hardening gate: Reviewer -> Security (or deferred/waived) -> QA.

  • On pass: The story is complete. Update spec/ACTIVE.md: status: done if this was the last story for the feature, otherwise advance current_story to the next one and reset current_gate: 4.
  • On fail: Hand off to the Developer with a clear, actionable list of failed tests and reproduction steps.

Inputs

  • spec/ACTIVE.md (to determine the active feature slug)
  • spec/<slug>/EPIC-*.md (for story acceptance criteria and security_review policy)
  • spec/<slug>/PLAN.md (for implementation context)
  • The implemented code changes.

Outputs

  • A test matrix mapping acceptance criteria to test cases and their results (Pass/Fail).
  • A defect log with Critical/High/Medium/Low severity and precise reproduction steps for any failures.
  • A final quality verdict: Pass or Fail.

Read the full file on GitHub · 53 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. 2d ago First seen · 53 lines · 20 tokens per session scan A 593dad942465

Subscribe to this mod's changes

sdp.qa is an agent published in the GitHub repository WojcikMM/spec-development-protocol (2 stars, last pushed 22d ago), licensed MIT. It adds 20 tokens to every session and 574 once invoked, about $0.0001 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.