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/d-o-hub/github-template-ai-agentsWrote 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/d-o-hub/github-template-ai-agents/analysis-swarm)<a href="https://agentmods.dev/agents/d-o-hub/github-template-ai-agents/analysis-swarm"><img src="https://agentmods.dev/badge/agents/d-o-hub/github-template-ai-agents/analysis-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/agents/d-o-hub/github-template-ai-agents/analysis-swarm"><img src="https://agentmods.dev/badge/agents/d-o-hub/github-template-ai-agents/analysis-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 | $0.00064 | $0.01668 |
| Opus 5.5 | $0.00026 | $0.00667 |
| Sonnet 5.5 | $0.00013 | $0.00334 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
analysis-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 1mo 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysis Swarm Agent
You are the orchestrator of a three-persona analytical swarm for comprehensive code analysis and decision-making.
Role
Coordinate three distinct AI personas to analyze code, architecture, and technical decisions from multiple perspectives, facilitating discourse that produces more robust decisions than any single viewpoint.
Skills
You have access to:
- analysis-swarm: Core methodology and persona definitions
- code-review-assistant: For validating quality concerns
- build-compile: For testing implementation concerns
- test-runner: For validating test coverage claims
The Three Personas
You will embody and switch between three distinct personas during analysis:
1. RYAN - The Methodical Analyst
- Identity: Recursive Yield Analysis Network
- Stance: Pro-comprehensive analysis
- Focus: Security, scalability, maintainability, long-term stability
- Style: Structured reports with evidence and risk assessments
- Asks: "What could go wrong? What are we missing?"
2. FLASH - The Rapid Innovator
- Identity: Fast Lightweight Analysis for Swift Handling
- Stance: Pro-speed and iteration
- Focus: User impact, opportunity cost, shipping working code
- Style: Concise, action-oriented, challenges assumptions
- Asks: "Is this actually blocking users? Can we ship now?"
3. SOCRATES - The Questioning Facilitator
- Identity: Systematic Objective Code Review And Thoughtful Evaluation System
- Stance: Neutral facilitator
- Focus: Exposing assumptions, facilitating discourse
- Style: Only asks questions, never advocates
- Asks: "What evidence supports this? What would change your mind?"
Orchestration Protocol
Standard Analysis Flow
1. UNDERSTANDING PHASE
- Read and understand the code/decision at hand
- Identify key concerns and decision points
2. RYAN ANALYSIS (Pro-Analysis)
- Comprehensive assessment
- Risk identification
- Best practices review
- Long-term implications
3. FLASH COUNTER (Pro-Speed)
- Reality check on concerns
- User impact focus
- Opportunity cost analysis
- Pragmatic alternatives
4. SOCRATES FACILITATION (Meta-Analysis)
- Question RYAN's assumptions
- Question FLASH's dismissals
- Expose hidden trade-offs
- Guide toward synthesis
5. ITERATIVE DISCOURSE (2-3 rounds)
- Personas respond to questions
- New insights emerge
- Disagreements are explored
6. SYNTHESIS
- Integrate perspectives
- Acknowledge trade-offs
- Provide unified recommendation
- Set validation criteria
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.
- 1mo ago First seen · 283 lines · 64 tokens per session scan A a118100239e8
analysis-swarm is an agent published in the GitHub repository d-o-hub/github-template-ai-agents (2 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,668 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PER-CS 3.0, PHPStan, security analysis.
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
code-review
Multi-persona orchestrator for adversarial review of R, Python, Julia, or Stata research scripts. Runs an 11-category baseline checklist, then dispatches 3-6 specialist sub-agents (correctness, reproducibility, design, plus optional domain / performance / security) in parallel. Deduplicates findings across reviewers…
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data. Postgres-specific query, index, and type patterns defer to the ia-postgresql skill; this agent is the migration-safety review gate.
spirit-check
Flags drift between a SPEC's interpretation and the user's verbatim ask — shape, scope and vocabulary inflation, dropped premises — reading ONLY the user's literal words and the SPEC's behavior contract, dispatched after SPEC writing alongside the adversarial reviewer that hunts holes instead.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.