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-production-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-production-swarm)<a href="https://agentmods.dev/skills/summarybotng/summarybot-ng/qcsd-production-swarm"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/qcsd-production-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-production-swarm"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/qcsd-production-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 | $0.00068 | $0.02443 |
| Opus 5 | $0.00034 | $0.01222 |
| Sonnet 5 | $0.00014 | $0.00489 |
| Haiku 4.5 | $0.00007 | $0.00244 |
Grade A, and why
qcsd-production-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 8d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QCSD Production Swarm v1.0
Post-release production health assessment and QCSD feedback loop closure.
Overview
The Production Swarm assesses release health in the live production environment using DORA metrics, incident RCA, defect prediction, and cross-phase feedback loops. It renders a HEALTHY / DEGRADED / CRITICAL decision and is the only QCSD phase with dual responsibility: assessing current production health AND closing the feedback loop back to Ideation and Refinement phases.
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
TELEMETRY_DATA: Path to production telemetry, incident reports, and DORA metrics (required)RELEASE_ID: Release identifier for tracking (optional)OUTPUT_FOLDER: Where to save reports (default:${PROJECT_ROOT}/Agentic QCSD/production/)SLA_DEFINITIONS: Path to SLA/SLO target definitions (optional)
ENFORCEMENT RULES - READ FIRST
| Rule | Enforcement |
|---|---|
| E1 | You MUST spawn ALL THREE core agents in Step 2. No exceptions. |
| E2 | You MUST put all parallel Task calls in a SINGLE message. |
| E3 | You MUST STOP and WAIT after each batch. No proceeding early. |
| E4 | You MUST spawn conditional agents if flags are TRUE. No skipping. |
| E5 | You MUST apply HEALTHY/DEGRADED/CRITICAL logic exactly as specified in Step 5. |
| E6 | You MUST generate the full report structure. No abbreviated versions. |
| E7 | Each agent MUST read its reference files before analysis. |
| E8 | You MUST run BOTH feedback agents in Step 8 SEQUENTIALLY. Always. Both agents. |
| E9 | You MUST execute Step 7 learning persistence. No skipping. |
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-production-swarm.yaml 6.1 KB
- schemas/output.json 17 KB
- scripts/validate-config.json 442 B
- steps/01-flag-detection.md 8.7 KB
- steps/02-core-agents.md 16 KB
- steps/03-batch1-results.md 4.2 KB
- steps/04-conditional-agents.md 6.9 KB
- steps/05-decision-synthesis.md 5.5 KB
- steps/06-report-generation.md 4.8 KB
- steps/07-learning-persistence.md 6.2 KB
- steps/08-feedback-loop.md 5.1 KB
- steps/09-final-output.md 8.3 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.
- 8d ago First seen · 207 lines · 68 tokens per session scan A 2cc43bab055a
qcsd-production-swarm is a skill published in the GitHub repository summarybotng/summarybot-ng (2 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 2,443 once invoked, about $0.0003 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
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
continuous-learning
Use when a mistake, correction, or surprise taught the workspace something that must stick — a retro or postmortem, the same agent error corrected twice, a resolved bug's root cause, scattered notes-to-self — and route that lesson to the durable surface that fires next time. NOT a forward choice with alternatives…
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
skill-creator
Guide for creating effective agent skills. Use when you want to create a new skill, improve an existing skill, or learn best practices for skill development. Helps codify learned patterns into reusable, discoverable skills.
ai-native-production-ops
A method for operating an AI product after launch or during preparation for launch. It covers monitoring, metrics, failure handling, human corrections, feedback, and business or customer feedback loops.