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-workflowgit 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-workflow)<a href="https://agentmods.dev/skills/chadixearth/graphyloop/graphyloop-workflow"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/graphyloop-workflow/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-workflow"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/graphyloop-workflow.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 | $0.00060 | $0.01475 |
| Opus 5.5 | $0.00024 | $0.00590 |
| Sonnet 5.5 | $0.00012 | $0.00295 |
| Haiku 4.5 | $0.00006 | $0.00147 |
Grade A, and why
graphyloop-workflow 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 8d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GraphyLoop Workflow v2 (condensed)
The full rules live in the installed rules file (AGENTS.md) when your harness loads one. This is the same workflow in one page, for harnesses that do not: Oh My Pi, Gemini CLI, Claude Code and others. The user's explicit instruction and the project's own rules always win.
Tool names: OpenCode graphyloop_<tool>; Claude Code and DeepSeek Harness mcp__graphyloop__<tool>; Codex, Cursor, Oh My Pi, Gemini CLI bare <tool>. Below: bare names. If one is missing, run npx graphyloop doctor.
The 11 rules
- Recall first, record last.
memory_searchwith 2-4 keywords before planning; use hits, stay silent on a miss, never invent one. At the endmemory_storeONE dense line (decision/lesson/pattern/event). Never store credentials. Seeswarm-memory. - Size the work. 3 or fewer known files: do it inline (read, smallest edit, one targeted check, no dispatch, no memory calls). 4+ files or unmapped code is a build: rules 3-9.
- Context pack. One batched read pass writes
ctx-<slug>.md: per lanepath:line, the current code excerpt, the pattern to copy. Lanes start editing instead of rediscovering. - Freeze the contract. Same turn as dispatch, write
contract-<slug>.md(entities and columns, routes with request/response JSON and error codes, props, the test scenarios that define done, env keys). It is the only cross-lane dependency; if wrong, fix the contract, never drift. - One wave. All independent lanes in ONE parallel dispatch, one lane per layer (data, backend, frontend, tests, UI), strictly disjoint file sets, max 4 concurrent by default. Data runs alongside backend and frontend.
- Turn economy. Lanes batch reads, first edit by turn 5, done in about 25 turns; 40+ means mis-sized. End every BUILDER brief with:
Read the ctx pack and contract first, in ONE turn. Batch 2+ reads/searches into one parallel call; read with line ranges; never re-read a file; first edit by turn 5; do not run project-wide lint/test/build — the driver does.Wave-0 (writes ctx + contract):Batch 2+ reads/searches into one parallel call; read with line ranges; never re-read a file; write the ctx pack and contract before anything else.Integration/verify/deploy lanes:Read the ctx pack and contract first, in ONE turn. Batch 2+ reads/searches into one parallel call; read with line ranges; never re-read a file. - No polling. Servers, builds, deploys and renders run in the background or via the tool's own blocking command (
vercel inspect --wait,gh run watch). Never sleep-loop. - Verify by running. Smoke the changed path and quote the decisive output line. Tests alone are not proof; check UI in a real browser; check artifacts by viewing the rendered file. Run lint/typecheck/test/build once, centrally, after lanes land.
- Audit is conditional. Reviewer and security agents only for auth, RBAC, payments, uploads, secrets, data/tenant boundaries, or a diff you cannot read end to end.
- Artifact wave (posters, decks, PDFs, video): freeze
brief-<slug>.md, hero piece first, one lane per artifact. - Evidence-first report: Changed / Files / Verified (command plus verbatim output) / Skills / Blocked. Never claim a check that did not run.
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.
- 8d ago First seen · 47 lines · 60 tokens per session scan A 5539229a0bd5
graphyloop-workflow is a skill published in the GitHub repository chadixearth/graphyloop (3 stars, last pushed 9d ago), licensed MIT. It adds 60 tokens to every session and 1,475 once invoked, about $0.0002 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 2026-10-09.
Other skills, from other repositories
aikito
Operate Aikito workspaces and resources, including reading inbox notes, managing memory, skills, projects, MCP servers, subagents, and synchronization.
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.
island
A discrete, loadable brain.
sync
Pull and push your brain.
memory
When and how to use Gobby's persistent memory system effectively. Covers decision frameworks for what to remember, how to write durable memories, and maintenance patterns.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.