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.
npx skills add summarybotng/summarybot-ng --skill qcsd-refinement-swarmgit clone --depth 1 https://github.com/summarybotng/summarybot-ngWrote 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/summarybotng/summarybot-ng/qcsd-refinement-swarm)<a href="https://agentmods.dev/skills/summarybotng/summarybot-ng/qcsd-refinement-swarm"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/qcsd-refinement-swarm/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/summarybotng/summarybot-ng/qcsd-refinement-swarm"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/qcsd-refinement-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00036 | $0.01496 |
| Opus 5 | $0.00018 | $0.00748 |
| Sonnet 5 | $0.00007 | $0.00299 |
| Haiku 4.5 | $0.00004 | $0.00150 |
Grade A, and why
qcsd-refinement-swarm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QCSD Refinement Swarm v1.0
Shift-left quality engineering swarm for Sprint Refinement sessions.
Overview
The Refinement Swarm takes user stories that passed Ideation and prepares them for Sprint commitment using SFDIPOT product factors, BDD scenarios, and INVEST validation. It renders a READY / CONDITIONAL / NOT-READY decision.
QCSD Phase Positioning
| Phase | Swarm | Decision | When |
|---|---|---|---|
| Ideation | qcsd-ideation-swarm | GO / CONDITIONAL / NO-GO | PI/Sprint Planning |
| Refinement | qcsd-refinement-swarm | READY / CONDITIONAL / NOT-READY | Sprint Refinement |
| Development | qcsd-development-swarm | SHIP / CONDITIONAL / HOLD | During Sprint |
| Verification | qcsd-cicd-swarm | RELEASE / REMEDIATE / BLOCK | Pre-Release / CI-CD |
| Production | qcsd-production-swarm | HEALTHY / DEGRADED / CRITICAL | Post-Release |
Parameters
STORY_CONTENT: User story with acceptance criteria (required)OUTPUT_FOLDER: Where to save reports (default:${PROJECT_ROOT}/Agentic QCSD/refinement/)
ENFORCEMENT RULES - READ FIRST
| Rule | Enforcement |
|---|---|
| E1 | MUST spawn ALL THREE core agents in Step 2. |
| E2 | MUST put all parallel Task calls in a SINGLE message. |
| E3 | MUST STOP and WAIT after each batch. |
| E4 | MUST spawn conditional agents if flags are TRUE. |
| E5 | MUST apply READY/CONDITIONAL/NOT-READY logic exactly. |
| E6 | MUST generate the full report structure. |
| E7 | Each agent MUST read its reference files before analysis. |
| E8 | MUST apply qe-test-idea-rewriter transformation in Step 8. |
| E9 | MUST execute Step 7 learning persistence. |
Step Execution Protocol
Execute steps sequentially by reading each step file with the Read tool.
Steps
- Flag Detection --
steps/01-flag-detection.md-- Analyze story content, evaluate all 7 flags - Core Agents --
steps/02-core-agents.md-- Spawn qe-product-factors-assessor, qe-bdd-generator, qe-requirements-validator - Batch 1 Results --
steps/03-batch1-results.md-- Wait and extract metrics - Conditional Agents --
steps/04-conditional-agents.md-- Spawn flagged agents - Decision Synthesis --
steps/05-decision-synthesis.md-- Apply READY/CONDITIONAL/NOT-READY logic - Report Generation --
steps/06-report-generation.md-- Generate refinement report - Learning Persistence --
steps/07-learning-persistence.md-- Store findings to memory - Transformation --
steps/08-transformation.md-- Run test idea rewriter on all test ideas - Final Output --
steps/09-final-output.md-- Display completion summary
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/qcsd-refinement-swarm.yaml 3.0 KB
- schemas/output.json 19 KB
- scripts/validate-config.json 442 B
- steps/01-flag-detection.md 3.2 KB
- steps/02-core-agents.md 1.8 KB
- steps/03-batch1-results.md 1.1 KB
- steps/04-conditional-agents.md 1.3 KB
- steps/05-decision-synthesis.md 1.4 KB
- steps/06-report-generation.md 1.3 KB
- steps/07-learning-persistence.md 1.3 KB
- steps/08-transformation.md 1.1 KB
- steps/09-final-output.md 2.3 KB
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.
- 5d ago First seen · 146 lines · 36 tokens per session scan A 09d0317b7580
qcsd-refinement-swarm is a skill published in the GitHub repository summarybotng/summarybot-ng (2 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 1,496 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 2026-09-03.
Other skills, from other repositories
bdd-mathematical-verification
BDD-Driven Mathematical Content Verification Skill Combines Behavior-Driven Development with mathematical formula extraction, verification, and transformation using: Cucumber/Gherkin for specification RSpec for implementation verification mathpix-gem for LaTeX/mathematical content extraction Pattern matching on syntax…
acceptance-criteria-given-when-then
Use this skill when writing test-first, behavior-driven acceptance criteria in Given/When/Then format for a Salesforce user story. Covers happy path, edge cases, negative paths, permission boundaries, and data-state preconditions so the AC block can drive UAT scripts and Apex test design downstream. Trigger keywords…
Forge
Autonomous quality engineering swarm that forges production-ready code through continuous behavioral verification, exhaustive E2E testing, and self-healing fix loops. Combines DDD+ADR+TDD methodology with BDD/Gherkin specifications, 7 quality gates, defect prediction, chaos testing, and cross-context dependency…
Behat BDD Testing
PHP BDD testing with Behat framework using Gherkin feature files, Mink browser extension, context classes, and Symfony integration for behavior-driven acceptance testing.
BDD/Cucumber Patterns
Behavior-Driven Development skill using Cucumber, covering feature files, step definitions, Gherkin best practices, data tables, scenario outlines, and hooks.
testing
TDD/BDD testing principles. Use when writing tests, reviewing test coverage, setting up testing, or discussing test strategy and test architecture.