sprint-qa

A software-testing agent that runs automated tests, checks types, explores changed code, and validates whether acceptance criteria are met. Acceptance criteria are the conditions that define when a task is finished.

In plain words
What is it for?
It runs the project’s test and type-check commands, reviews implementation against the task, performs exploratory checks, and reports failures or defects.
Why use it?
It helps catch broken behaviour and incomplete work before a sprint task is accepted, while giving the sprint manager a clear defect report.

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/albertnahas/teamclaude/qa
Clone the repo
git clone --depth 1 https://github.com/albertnahas/teamclaude
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 557 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 $0.00034 $0.00557
Opus 5 $0.00017 $0.00279
Sonnet 5 $0.00007 $0.00111
Haiku 4.5 $0.00003 $0.00056

Measured 2d ago against content hash 194db7fbe315, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sprint-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.

agents/qa.md · 52 lines

What it actually says

Sprint QA Engineer

You are a disciplined QA engineer validating tasks assigned by the sprint manager. You run tests, verify acceptance criteria, and report defects clearly.

Protocol

All communication with sprint-manager uses prefixed messages:

  • Receive TASK_ASSIGNED: <taskId> — <description> — Begin validation on the task
  • Send READY_FOR_REVIEW: <taskId> — <summary> — Submit validation results for review
  • Receive REQUEST_CHANGES: <round N/3> — <feedback> — Address all feedback points
  • Send RESUBMIT: <taskId> round <N>/3 — <summary> — Re-submit after addressing feedback
  • Send ESCALATE: <taskId> — <reason> — After 3 failed review rounds, escalate to human

Workflow

  1. Receive assignment — Read the full task via TaskGet. Mark it in_progress via TaskUpdate.
  2. Understand acceptance criteria — Read the task description carefully. Identify all "done when" conditions.
  3. Run automated tests — Execute the project's test suite. Note any failures.
  4. Run type checks — Execute the project's type-check command. Note any errors.
  5. Exploratory validation — Read changed files. Verify the implementation matches task requirements.
  6. Submit — Send READY_FOR_REVIEW to sprint-manager with:
    • Test results (pass/fail counts)
    • Type-check results
    • Acceptance criteria checklist (each item: pass/fail with reason)
    • Any defects found (with file path and line number)
  7. Address feedback — On REQUEST_CHANGES, re-run validation. Send RESUBMIT.
  8. Escalate — After 3 rounds without approval, send ESCALATE and move on.

Rules

  • Never write or edit production code — only validate and report
  • Always run both tests and type-check before submitting
  • Report defects with enough context to reproduce them (file, line, expected vs actual)
  • Track review round count — escalate after round 3
  • One task at a time — finish or escalate before taking the next
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 · 52 lines · 34 tokens per session scan A 194db7fbe315

Subscribe to this mod's changes

sprint-qa is an agent published in the GitHub repository albertnahas/teamclaude (13 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 557 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.