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 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/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/andrew-hernandez-paragon/code-graph-context/swarm"><img src="https://agentmods.dev/badge/skills/andrew-hernandez-paragon/code-graph-context/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 | $0.00095 | $0.02833 |
| Opus 5.5 | $0.00038 | $0.01133 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 3d ago), licensed MIT. It adds 95 tokens to every session and 2,833 once invoked, about $0.0004 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 2026-08-30.
swarm compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| swarmandrew-hernandez-paragon/code-graph-context | Skill | 17 | 3d ago | MIT | A | 95 | Claude Code, Codex |
| performing-cloud-asset-inventory-with-cartographyxalgorix/xalgorix | Skill | 1.3k | today | Apache-2.0 | A | 49 | Claude Code, Codex |
| implementation-readinessHoangNguyen0403/agent-skills-standard | Skill | 584 | yesterday | MIT | A | 27 | Codex |
| skill-benchmarkHoangNguyen0403/agent-skills-standard | Skill | 584 | yesterday | MIT | A | 16 | Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 278 | today | Apache-2.0 | A | 54 | Claude Code, Codex |
| opik-diagnosecomet-ml/opik-mcp | Skill | 226 | 7d ago | Apache-2.0 | A | 187 | Claude Code |
| common-observabilityHoangNguyen0403/agent-skills-standard | Skill | 584 | yesterday | MIT | A | 46 | Claude Code, Codex |