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 skills/andrew-hernandez-paragon/code-graph-context/swarmnpx skills add andrew-hernandez-paragon/code-graph-context --skill swarmgit clone --depth 1 https://github.com/andrew-hernandez-paragon/code-graph-contextWrote 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/andrew-hernandez-paragon/code-graph-context/swarm)<a href="https://agentmods.dev/skills/andrew-hernandez-paragon/code-graph-context/swarm"><img src="https://agentmods.dev/badge/skills/andrew-hernandez-paragon/code-graph-context/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 5.1 | $0.00095 | $0.02833 |
| Opus 5 | $0.00048 | $0.01417 |
| Sonnet 5 | $0.00019 | $0.00567 |
| Haiku 4.5 | $0.00010 | $0.00283 |
Grade A, and why
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 — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swarm Coordination System
Execute complex, multi-file codebase changes with parallel AI agents that coordinate through the code graph.
Two Coordination Mechanisms
| Mechanism | Pattern | Best For |
|---|---|---|
| Pheromones | Stigmergy (indirect) | Exploration, claiming territory, avoiding conflicts |
| Task Queue | Blackboard (explicit) | Defined work items, dependencies, progress tracking |
Use both together: tasks define WHAT to do, pheromones prevent WHO from colliding.
Quick Start: Manual Orchestration
For multi-file tasks, decompose and post tasks manually:
// 1. Create a swarm and post tasks
swarm_post_task({
projectId: "<PROJECT>",
swarmId: "swarm_<slug>",
title: "Implement feature X",
description: "...",
type: "implement",
createdBy: "orchestrator"
})
// 2. Spawn workers to claim and execute tasks
Task({
subagent_type: "general-purpose",
run_in_background: false, // CRITICAL: must be false for MCP tools
prompt: "Claim and execute task from swarm_<slug>..."
})
Core Concepts
Swarm ID
Every swarm needs a unique ID for coordination and cleanup:
const swarmId = `swarm_${Date.now()}`
Node IDs
NEVER fabricate node IDs. They must come from graph tool responses:
// Get from search
const result = search_codebase({ projectId, query: "..." })
const nodeId = Object.keys(result.nodes)[0]
// Get from traversal
const result = traverse_from_node({ projectId, filePath: "..." })
const nodeId = result.startNodeId
Format: proj_<12hex>:<NodeType>:<16hex>
Pheromone Types
| Type | Half-Life | Meaning |
|---|---|---|
exploring |
2 min | Reading/browsing |
claiming |
1 hour | Reserved territory |
modifying |
10 min | Actively editing |
completed |
24 hours | Work finished |
blocked |
5 min | Stuck/waiting |
warning |
Never | Do not touch |
proposal |
1 hour | Awaiting approval |
needs_review |
30 min | Review requested |
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 · 419 lines · 95 tokens per session scan A 1096e44bd139
swarm is a skill published in the GitHub repository andrew-hernandez-paragon/code-graph-context (17 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 2,833 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
performing-cloud-asset-inventory-with-cartography
Perform comprehensive cloud asset inventory and relationship mapping using Cartography to build a Neo4j security graph of infrastructure assets, IAM permissions, and attack paths across AWS, GCP, and Azure.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
planning-and-task-breakdown
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.