qa-cycle

A repeated quality-assurance and bug-fixing workflow that runs project checks, validates requirements and edge cases, and continues until the reported issues pass.

In plain words
What is it for?
Validating completed changes, checking bug fixes, and performing a final verification cycle before creating a pull request.
Why use it?
It catches failed tests, lint errors, regressions, and unmet acceptance criteria before a change is submitted for review.

Skill for Claude CodeCodex

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 skills/guild-agents/guild/qa-cycle
Any agent
npx skills add Guild-Agents/guild --skill qa-cycle
Clone the repo
git clone --depth 1 https://github.com/Guild-Agents/guild

Made for: Claude Code, Codex.

Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 953 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 $0.00011 $0.00953
Opus 5 $0.00005 $0.00477
Sonnet 5 $0.00002 $0.00191
Haiku 4.5 $0.00001 $0.00095

Measured yesterday against content hash f362fab10e11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-cycle 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 yesterday.

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-cycle/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Cycle

Runs a QA validation cycle followed by bugfix until all criteria pass clean. Useful for validating implementations without the full build-feature pipeline.

When to use

  • After implementing changes that need validation
  • To verify that a bug fix did not introduce regressions
  • As a final cycle before creating a PR

Usage

/qa-cycle

Process

Step 1 — Automated verification (mandatory)

Before invoking the QA agent, run the project verification commands. The specific commands are in the "CLI commands" section of CLAUDE.md:

  1. Run project tests (e.g., npm test) — record result and output
  2. Run project lint (e.g., npm run lint) — record result and output
  3. If any fail, this becomes input for the QA report as an automatic Blocker bug

Step 2 — QA Validation

Invoke the QA agent using Task tool with model: "sonnet" (execution tier):

  1. Read .claude/agents/qa.md to assume the QA role
  2. Read CLAUDE.md for context
  3. Receive the test and lint results from Step 1
  4. If tests or lint failed, include them as Blocker bugs in the report
  5. Review the acceptance criteria for the current task (if provided)
  6. Validate edge cases and error scenarios
  7. Report results

Step 3 — Bugfix (if there are bugs)

If QA reports bugs (including test/lint failures), invoke the Bugfix agent using Task tool with model: "sonnet" (execution tier):

  1. Read .claude/agents/bugfix.md to assume the Bugfix role
  2. Receive the QA bug report as input
  3. Diagnose the root cause of each bug
  4. Implement the minimal fix
  5. Verify that the fix resolves the issue
  6. Run tests and lint to confirm no regressions were introduced

Step 4 — Re-validation

Return to Step 1 (automated verification) to re-validate after the bugfix. Maximum 3 verification-QA-bugfix cycles to prevent infinite loops.

Step 5 — Final result

Present the result:

  • Approved: All criteria pass, no pending bugs
  • With warnings: Passes but there are minor warnings
  • Rejected: There are critical bugs that could not be resolved — escalate to the Tech Lead

Read the full file on GitHub · 118 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. yesterday First seen · 118 lines · 11 tokens per session scan A f362fab10e11

Subscribe to this mod's changes

qa-cycle is a skill published in the GitHub repository Guild-Agents/guild (4 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 953 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.

Related

Other skills, from other repositories

codebase-memory

Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions…

narumiruna/pi-extensions · 98 tokens

using-pi-subagents

Operate pi-subagents jobs safely, including direct-work decisions, least-privilege tool selection, thinking-level selection, delegation, bidirectional messaging, parallel starts, timeout selection, waiting, cancellation, result handling, verification, and writer isolation.

narumiruna/pi-extensions · 54 tokens

herdr

Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires…

narumiruna/pi-extensions · 74 tokens

laravel-actions

Build, refactor, and troubleshoot Laravel Actions using lorisleiva/laravel-actions. Use when implementing reusable action classes (object/controller/job/listener/command), converting service classes/controllers/jobs into actions, orchestrating workflows via faked actions, or debugging action entrypoints and wiring.

coollabsio/coolify · 62 tokens

debugging-output-and-previewing-html-using-ray

Use when user says "send to Ray," "show in Ray," "debug in Ray," "log to Ray," "display in Ray," or wants to visualize data, debug output, or show diagrams in the Ray desktop application.

coollabsio/coolify · 58 tokens

Shade dropdown surface contract

DropdownMenu, Select, and Popover share one visual recipe (bg-surface-elevated-2 + border-border/60 dark:border-border/30 + shadow-md). Change them together. Trigger when editing any of those three Shade files.

TryGhost/Ghost · 54 tokens