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 josix/agent-flow --skill graphify-usagegit clone --depth 1 https://github.com/josix/agent-flowWrote 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/josix/agent-flow/graphify-usage)<a href="https://agentmods.dev/skills/josix/agent-flow/graphify-usage"><img src="https://agentmods.dev/badge/skills/josix/agent-flow/graphify-usage/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/josix/agent-flow/graphify-usage"><img src="https://agentmods.dev/badge/skills/josix/agent-flow/graphify-usage.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 | $0.00036 | $0.01623 |
| Opus 5.5 | $0.00014 | $0.00649 |
| Sonnet 5.5 | $0.00007 | $0.00325 |
| Haiku 4.5 | $0.00004 | $0.00162 |
Grade A, and why
graphify-usage 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 18d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graphify Usage
Query the knowledge graph effectively, interpret results accurately, and stay within token budgets.
Overview
The graphify MCP server exposes the codebase as a pre-built knowledge graph stored in graphify-out/graph.json. The graph encodes structural relationships between concepts, modules, and files extracted by the graphify pipeline. This skill governs when, how, and with what discipline agents should query it.
Owner: Riko (Explorer Agent) — Riko is the primary graph query agent and owns interpretation of results. Consumers: Senku (Planner Agent), Lawliet (Reviewer Agent) — both may consult the graph during planning and review, but Riko is the preferred query agent for deep exploration. Out of scope: Loid (Executor) and Alphonse (Verifier) do NOT have graph access by design. Loid performs file writes and needs test output, not structural queries; Alphonse runs verification commands that cannot rely on graph freshness. This enforces the one-writer invariant: only agents that need structural context hold graph tool permissions.
All 7 tools are accessed via the MCP prefix mcp__plugin_agent-flow_graphify__*. See references/tool-reference.md for full signatures.
When to Query the Graph vs. Grep
Use the graph when you need structural relationships. Use grep when you need literal text matches.
| Trigger condition | Preferred approach |
|---|---|
| "What modules import X?" / dependency mapping | Graph: get_neighbors with relation_filter |
| "What is the main entry point?" / orientation | Graph: graph_stats then god_nodes |
| "How does component A connect to component B?" | Graph: shortest_path |
| "Which community does file F belong to?" | Graph: get_community on node label |
"Find the string literal TODO: fix" |
Grep |
"Find all files that define function parse_args" |
Grep (pattern match) |
| "What does a specific config key say?" | Read the file directly |
| File is freshly edited (within this session) | Grep/Read — graph may be stale |
Graph does not exist at graphify-out/graph.json |
Grep/Read only |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 18d ago Changed · +1 lines 5ecfe64678d0
- 1mo ago First seen · 125 lines · 36 tokens per session scan A 63382d0f17e9
graphify-usage is a skill published in the GitHub repository josix/agent-flow (7 stars, last pushed 17d ago), licensed MIT. It adds 36 tokens to every session and 1,623 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.