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 agentmods add agents/eco-ansible-content/agentic-workflows/invoke-swarmgit 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/invoke-swarm)<a href="https://agentmods.dev/agents/eco-ansible-content/agentic-workflows/invoke-swarm"><img src="https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/invoke-swarm.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00943 |
| Opus 5 | $0.00000 | $0.00472 |
| Sonnet 5 | $0.00000 | $0.00189 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
invoke-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 4d 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.
This is a copy
100% identical to windows-collection-swarm-invoke-swarm — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Direct Swarm Invocation
Use this to directly invoke the Lead Architect agent with a Jira Epic, bypassing the skill wrapper.
Direct Invocation
Copy this Agent call and replace <EPIC_KEY> with your Jira Epic:
Agent(
subagent_type: "lead-architect",
description: "Build Windows collection from <EPIC_KEY>",
prompt: """Build a complete Windows Ansible collection from Jira Epic <EPIC_KEY>.
Configuration:
- Epic Key: <EPIC_KEY>
- Namespace: auto-detect from Epic
- Collection Name: auto-detect from Epic
- Batch Size: 3 modules per batch
Execute the full Jarvis Framework lifecycle with extreme autonomy:
Phase 1: Ingestion
- Spawn jira-ingestion-specialist agent
- Provide Epic key: <EPIC_KEY>
- Wait for module backlog generation in docs/plans/module_backlog.md
Phase 2: Foundation
- Spawn foundation-specialist agent
- Provide namespace and collection name from Epic analysis
- Wait for workspace scaffolding at ~/agentic-workflow-collections/<namespace>/<name>/
Phase 3: Build Loop (Repeat until backlog 100% complete)
- Group uncompleted modules into batches of 3
- For each batch:
a. Spawn 3 module-worker agents in parallel
b. Assign 1 module per worker from backlog
c. Wait for all workers to complete
d. Spawn qa-coordinator agent
e. Wait for QA to approve batch (4-stage loop + peer review)
f. Mark batch as [x] DONE in backlog
g. Every 10 modules: Spawn refactor-specialist, wait for refactor completion
Phase 4: Delivery
- When 100% of backlog marked [x] DONE:
a. Spawn release-specialist agent
b. Wait for four-pillar audit completion
c. Wait for git commit and push
d. Report final collection location and statistics
Autonomy Rules (CRITICAL):
- NEVER ask for permission between phases - proceed automatically
- Self-correct failures with 3 attempts before reporting
- Make ALL technical decisions autonomously (parameter names, types, implementation)
- Skip ALL brainstorming/design phases - architecture is pre-defined
- Report ONLY on final completion or unrecoverable errors after 3 attempts
Agent Definitions Location:
All agents are defined in: ~/.claude/agents/windows-collection-swarm/
Agent Spawning:
Use the Agent tool to spawn sub-agents:
- jira-ingestion-specialist
- foundation-specialist
- module-worker (spawn multiple in parallel for batches)
- qa-coordinator
- refactor-specialist
- release-specialist
Begin execution immediately. Do not wait for user confirmation."""
)
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.
- 4d ago First seen · 141 lines · 0 tokens per session scan A 7aaed8b17b66
invoke-swarm is an agent published in the GitHub repository eco-ansible-content/agentic-workflows (2 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 943 tokens. A static security scan graded it A with 0 findings. It is 100% identical to windows-collection-swarm-invoke-swarm, differing in 2 lines, and is treated as a copy.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
speckit.squad.status
Show alignment between your spec, tasks, and Squad agents.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…