mako-trace

mako-trace is a skill for Claude Code, Codex from drhalto/agentmako. It costs 70 tokens per session (910 once invoked), scanned A, original, Apache-2.0.

A Mako guide for tracing a specific route, schema object, file, table, RPC, or error through indexed project evidence. A schema describes the structure of data, and an RPC is a callable service or database operation.

In plain words
What is it for?
Use it to trace routes, schema usage, file health, authentication paths, tables, RPCs, edges, and error messages.
Why use it?
It helps connect a known target to its implementation, references, dependencies, and supporting evidence. This makes focused debugging and impact checks easier to verify.

Skill for Claude CodeCodex

Part of the mako-ai plugin — 8 skills, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/drhalto/agentmako/mako-trace
Any agent
npx skills add drhalto/agentmako --skill mako-trace
Clone the repo
git clone --depth 1 https://github.com/drhalto/agentmako

Made for: Claude Code, Codex.

Or install mako-ai, the plugin that ships this one along with the rest of its 8 skills, 1 MCP server.

Wrote 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.

agentmods badge for mako-trace

README.md
[![agentmods](https://agentmods.dev/badge/skills/drhalto/agentmako/mako-trace.svg)](https://agentmods.dev/skills/drhalto/agentmako/mako-trace)
Your own site
<a href="https://agentmods.dev/skills/drhalto/agentmako/mako-trace"><img src="https://agentmods.dev/badge/skills/drhalto/agentmako/mako-trace.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 910 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00070 $0.00910
Opus 5 $0.00035 $0.00455
Sonnet 5 $0.00014 $0.00182
Haiku 4.5 $0.00007 $0.00091

Measured 5d ago against content hash 3f56671249ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mako-trace 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 5d 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.

mako-ai-claude-plugin/skills/mako-trace/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mako Trace

Use this skill for focused evidence traces around a known target. The output should help the user understand what implements the target, what depends on it, and what evidence supports the answer.

Targeted Answer Tools

route_trace

Use to find the route handler, nearby files, and evidence for a route/API behavior.

  • Best when the user names a route, page, method/path pair, or route-like URL.
  • Pair with auth_path for authorization questions.
  • Pair with route_context when the user wants a wider route neighborhood.

schema_usage

Use to find where an indexed schema object, table shape, or validation type is defined and referenced.

  • Best for schema objects and type-ish entities.
  • Use before editing validation contracts or generated schema surfaces.
  • Pair with trace_table or table_neighborhood for database-backed entities.

file_health

Use to understand a file's role, dependents, risks, and likely blast radius.

  • Best before editing a central or unfamiliar file.
  • Pair with imports_impact for a deeper dependency view.
  • Do not use it for repo-wide orientation; use repo_map.

auth_path

Use to inspect likely authentication or authorization boundaries for a route, file, feature, or flow.

  • Best when the user asks what protects something or whether auth is enforced.
  • Pair with route_trace, route_context, and tenant_leak_audit when the risk is tenant or data-boundary related.
  • If no exact route, file, or feature matches, auth_path returns matched: false, reason, and a suggested cross_search fallback instead of throwing a batch-breaking error.
  • Do not overclaim; report evidence and uncertainty.

Composer Trace Tools

trace_file

Use for a compact file trace: symbols, imports, routes, schema touches, and notable relationships before editing.

preflight_table

Use before changing database-backed behavior to inspect table usage, RLS, relations, and common query paths.

trace_edge

Read the full file on GitHub · 114 lines

Changes

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.

  1. 5d ago First seen · 114 lines · 70 tokens per session scan A 3f56671249ea

Subscribe to this mod's changes

mako-trace is a skill published in the GitHub repository drhalto/agentmako (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 910 once invoked, about $0.0003 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.