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/drhalto/agentmako/mako-graphnpx skills add drhalto/agentmako --skill mako-graphgit clone --depth 1 https://github.com/drhalto/agentmakoWrote 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/drhalto/agentmako/mako-graph)<a href="https://agentmods.dev/skills/drhalto/agentmako/mako-graph"><img src="https://agentmods.dev/badge/skills/drhalto/agentmako/mako-graph.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 | $0.00072 | $0.00726 |
| Opus 5 | $0.00036 | $0.00363 |
| Sonnet 5 | $0.00014 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
mako-graph 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 4d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mako Graph
Use this skill when the user's question is about relationships rather than a single entity. Graph, import, and symbol tools help estimate impact, find paths, and plan changes from indexed project facts.
Graph Tools
graph_neighbors
Use to inspect immediate graph neighbors for a file, symbol, route, table, RPC, or other known node.
graph_path
Use to find evidence-backed paths between two known nodes.
- Best when the user asks whether A reaches B or how a route connects to a table/RPC/file.
- If the endpoints are ambiguous, use discovery or trace tools first.
flow_map
Use to map a higher-level flow across routes, components, services, tables, and RPCs.
- Best for end-to-end user stories or system behavior.
- Pair with
review_bundle_artifactwhen a flow is being reviewed pre-ship.
change_plan
Use to produce an evidence-backed edit plan and expected blast radius before implementation.
- Best when the user asks "what do we need to change?" or "what might break?"
- Pair with artifact tools when the plan needs a durable handoff.
Imports
imports_deps
Use to inspect direct imports and unresolved internal edges for one or more files.
imports_impact
Use to estimate downstream dependents and likely blast radius of changing a file/module.
imports_hotspots
Use to identify highly connected import hotspots.
imports_cycles
Use to detect or inspect circular dependencies.
Symbols
symbols_of
Use to list important symbols declared in a file.
exports_of
Use to list exported symbols from a file or module.
Feedback Logging
Log agent_feedback when a graph, import, or symbol result here was
notably useful, partial, noisy, stale, wrong, or wasted the turn. Skip
routine calls.
Required procedure (see /mako-ai:mako-guide for full rules and
reason-code vocabulary):
- Call
recall_tool_runsto get the prior run'srequestId. Do not fabricate one — if no run is recalled, skip feedback. - Call
agent_feedbackwithreferencedToolName,referencedRequestId,grade: "full" | "partial" | "no",reasonCodesfrom the starter vocabulary in/mako-ai:mako-guide, and a shortreason.
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.
- 4d ago First seen · 105 lines · 72 tokens per session scan A 58955df974ae
mako-graph is a skill published in the GitHub repository drhalto/agentmako (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 726 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 2026-08-30.
Other skills, from other repositories
ctxo-safe-edit
Use BEFORE editing, renaming, or deleting any function, class, or method, to avoid breaking dependents.
ctxo-understand
Use at the START of any code task (fix, extend, refactor, understand) before reading source files, to orient with ctxo and avoid going in the wrong direction.
ctxo-review-pr
Use when reviewing a PR, a diff, or recent changes, to get a full risk assessment in one call.
composer-prompting
Internal guidance for shaping a well-specified coding task into a tight Cursor/Composer prompt before delegating it via /cursor:delegate.
figma-design-system-to-design-md
Figma design system to design.md — Extract Figma design system into a structured design.md. Use when user says 'generate design.md', 'extract design system', 'design tokens to markdown', 'create design doc from Figma', 'Figma design system to design.md', or wants to document their design system from token files and…
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用，不要根据上下文自动触发。.