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 chadixearth/graphyloop --skill graphyloop-squadgit clone --depth 1 https://github.com/chadixearth/graphyloopWrote 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/chadixearth/graphyloop/graphyloop-squad)<a href="https://agentmods.dev/skills/chadixearth/graphyloop/graphyloop-squad"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/graphyloop-squad/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/chadixearth/graphyloop/graphyloop-squad"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/graphyloop-squad.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 | $0.00087 | $0.01559 |
| Opus 5 | $0.00044 | $0.00779 |
| Sonnet 5 | $0.00017 | $0.00312 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
graphyloop-squad 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 6d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GraphyLoop squad in dsh
dsh gives you delegation (subagent), skills, goals, todos and a real tool
sandbox. graphyloop adds the parts dsh deliberately leaves to composition:
a persistent memory that survives the session, a swarm ledger with wave
dependencies, and a squad of role prompts. This skill is the bridge — without
it the tools are present but nothing tells you the workflow they belong to.
When to activate
- Any request touching more than one file or more than one layer.
- Before planning anything: recall first (
mcp__graphyloop__memory_search). - Whenever you are about to delegate: pick a role prompt instead of improvising.
- After a decision, a fix, or a surprise: record it (
mcp__graphyloop__memory_store).
Skip it for a one-line answer or a single obvious edit — say so and just do it.
Tool names in this harness
The MCP bridge namespaces every tool, so the names are prefixed here and nowhere else in the graphyloop docs:
| Purpose | Tool |
|---|---|
| Recall before planning | mcp__graphyloop__memory_search |
| Record a decision / lesson / pattern | mcp__graphyloop__memory_store |
| Correct a wrong memory | mcp__graphyloop__memory_forget |
| Multi-layer feature -> wave plan | mcp__graphyloop__plan_feature |
Dispatch a wave (honours dependsOn) |
mcp__graphyloop__task_distribute |
| Close the loop on a task | mcp__graphyloop__task_record |
| Swarm + memory state | mcp__graphyloop__swarm_state |
| Roster | mcp__graphyloop__agent_spawn / mcp__graphyloop__agent_list |
| Credentials (masked, never a value) | mcp__graphyloop__secrets_status / mcp__graphyloop__secrets_set / mcp__graphyloop__env_sync |
| Database / deploy readiness | mcp__graphyloop__preflight |
| Which skills exist on this machine | mcp__graphyloop__skills_status |
If a call answers graphyloop CLI not found, the core is missing: tell the user
to run npx graphyloop install and stop guessing.
The squad, as dsh sees it
dsh has no agent files and no file-based slash commands: agents are compositions and commands are plugins. So the squad ships as prompt text you pass to dsh's own delegation tool.
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.
- 6d ago First seen · 116 lines · 0 tokens per session scan A c7d82a63b12f
graphyloop-squad is a skill published in the GitHub repository chadixearth/graphyloop (2 stars, last pushed 23d ago), licensed MIT. It adds 87 tokens to every session and 1,559 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
agf
Find local coding-agent sessions, inspect bounded metadata or summaries, and prepare a read-only resume plan with AGF. Use for finding prior work across agent CLIs, not for executing agents, deleting sessions, or reading full transcripts.
aikito
Install, configure, and operate Aikito workspaces, including memory, skills, project resources, MCP servers, subagents, adoption, synchronization, and status verification.
durable-memory
Git-versioned memory stored in the Aikito workspace, separate from any Agent's built-in memory. Use to search, retrieve, or persist cross-project and project-scoped durable knowledge, historical decisions, user preferences, or verified architecture constraints.
kirby-collections-and-navigation
Builds Kirby listings, pagination, search, filtering/sorting/grouping, and navigation menus. Use when implementing collection logic in templates/controllers/snippets.
kirby-debugging-and-tracing
Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.
kirby-headless-api
Exposes Kirby content to headless clients using the API, KQL, and JSON representations. Use when building API endpoints, KQL queries, or headless frontends.