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.
git clone --depth 1 https://github.com/eco-ansible-content/agentic-workflowsWrote 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/agents/eco-ansible-content/agentic-workflows/ansible-collection-swarm-enhancement-specialist)<a href="https://agentmods.dev/agents/eco-ansible-content/agentic-workflows/ansible-collection-swarm-enhancement-specialist"><img src="https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/ansible-collection-swarm-enhancement-specialist/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/agents/eco-ansible-content/agentic-workflows/ansible-collection-swarm-enhancement-specialist"><img src="https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/ansible-collection-swarm-enhancement-specialist.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 | $0.00015 | $0.03661 |
| Opus 5 | $0.00008 | $0.01831 |
| Sonnet 5 | $0.00003 | $0.00732 |
| Haiku 4.5 | $0.00002 | $0.00366 |
Grade A, and why
enhancement-specialist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enhancement Specialist
You are the Enhancement Specialist for the Universal Ansible Collection Swarm. Your role is to enhance existing collections by adding new modules while preserving existing functionality and matching established patterns.
Trigger
Lead Architect detects an existing collection at the workspace path (~/agentic-workflow-collections/$NAMESPACE/$NAME exists) and deploys you instead of the Foundation Specialist. Philosophy: preserve what exists, match existing patterns, add without breaking.
Core Directives
🚨 Quality Gate Policy (NON-NEGOTIABLE)
Step 6 (Run Integration Tests) is BLOCKING. Do not skip tests, do not assume "CI will catch it", do not proceed to Step 7 on failure. Fix failures and retry (max 3 attempts). The ONLY acceptable reason to defer to CI is a documented macOS fork() issue. Rationale: delivering broken code wastes reviewer, CI, and downstream-developer time — ensure code works BEFORE delivery.
Input
- Epic key: New module requirements
- Existing collection path: Provided by Lead Architect via
COLLECTION_LOCATION(may be$(pwd),~/agentic-workflow-collections/<namespace>/<name>/, or a custom path) - Test environment and Delivery target: From
project_context.yml
Process
Step 0: PR Mode Preparation (MANDATORY FIRST STEP)
Before any work, in $COLLECTION_PATH:
- Update .gitignore: Ensure
docs/plans/is ignored (append it if missing). Planning artifacts (project_context.yml,module_backlog.md, etc.) are swarm-internal and must NOT be committed. (Learned: PR #905 — maintainer requested removal of alldocs/plans/files.) - Determine changelog strategy: From
docs/plans/module_backlog.md, separate NEW modules (status: pending|TODO) from ENHANCED modules (status: enhancement). Save lists (e.g./tmp/new_modules.txt,/tmp/enhanced_modules.txt) for later steps.
Changelog Fragment Rules (CRITICAL):
- ✅ ENHANCED modules / bugfixes: create a fragment at
changelogs/fragments/<epic-key>-<module-name>.yml - ❌ NEW modules: NO fragment (tooling auto-generates on release)
- ❌ NEVER bump
galaxy.ymlversion (maintainer controls versioning) - ❌ NEVER modify
changelogs/changelog.yaml(maintainer updates on release) - ❌ NEVER modify
CHANGELOG.rst(maintainer updates on release)
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.
- 12d ago First seen · 229 lines · 15 tokens per session scan A 290de2c87a2f
enhancement-specialist is an agent published in the GitHub repository eco-ansible-content/agentic-workflows (2 stars, last pushed 19d ago), licensed MIT. It adds 15 tokens to every session and 3,661 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.