What is trace-matrix?

A code-to-documentation tracing tool for backend systems. It compares HTTP endpoints, gRPC methods, database structures, processing stages, and other code entry points with a central matrix of which web, Mac, and database surfaces use them.

Use it to generate a checklist and update the matrix for HTTP, gRPC, database, pipeline, tuning, or all supported surface groups.

It helps keep the mapping accurate as backend code changes, so undocumented or incorrectly marked interfaces are easier to find.

How banshee-data/velocity.report configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to banshee-data/velocity.report. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/banshee-data/velocity.report/main/.claude/skills/trace-matrix/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/banshee-data/velocity.report

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/banshee-data/velocity.report/trace-matrix/github.svg)](https://agentmods.dev/skills/banshee-data/velocity.report/trace-matrix)

Your own site

<a href="https://agentmods.dev/skills/banshee-data/velocity.report/trace-matrix"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/trace-matrix/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/banshee-data/velocity.report/trace-matrix"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/trace-matrix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,280 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.02280
Opus 5.5	$0.00014	$0.00912
Sonnet 5.5	$0.00007	$0.00456
Haiku 4.5	$0.00003	$0.00228

Measured 14d ago against content hash 17ff261ace0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trace-matrix 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 14d 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.

.claude/skills/trace-matrix/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: trace-matrix

Maintain data/structures/MATRIX.md: the canonical mapping of every backend surface (HTTP endpoints, gRPC methods, DB tables/columns, pipeline stages, structs, tuning params, cmd/ entry points, debug routes) to three consumer surfaces: DB, Web, Mac.

Usage

/trace-matrix
/trace-matrix http
/trace-matrix grpc
/trace-matrix db
/trace-matrix pipeline
/trace-matrix tuning
/trace-matrix all

Without an argument, process all task groups sequentially (may require multiple passes if context is limited).

Procedure

1. Generate the checklist

python3 scripts/list-matrix-fields.py --checklist

This scans Go, Proto, Swift, SQL, and selected repo metadata and outputs a markdown checklist across 5 task groups, each sized for one context window.

2. Read the current matrix

Read data/structures/MATRIX.md to understand existing surface marks. This file is the ground truth to update.

§11 is a reference inventory of Go report pipeline files only. Do not assign DB/Web/Mac surface marks to that section.

3. Trace one task group at a time

HTTP API surfaces (§1, §2)

Sections: §1 Radar HTTP, §2 LiDAR HTTP

For each endpoint, read the Go handler function
Check DB: does the handler call any db.* or store.* method?
Check Web: search web/src/ for fetch() calls to this path
Check Mac: search tools/visualiser-macos/ for HTTP calls to this path

Key files:

internal/api/server.go: radar HTTP handlers
internal/lidar/server/routes.go: LiDAR route registration and core HTTP handlers
internal/lidar/server/track_api.go: track API handlers
internal/lidar/server/run_track_api.go: run/track API handlers
internal/lidar/server/clip_api.go: scene and evaluation handlers
internal/api/lidar_labels.go: label API handlers
web/src/lib/api/: Svelte fetch calls
tools/visualiser-macos/VelocityVisualiser/: Mac HTTP calls

gRPC + proto surfaces (§3, §14)

Sections: §3 gRPC methods, §14 FrameBundle proto fields

Read the full file on GitHub · 222 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.

14d ago Changed 17ff261ace0c
1mo ago First seen · 222 lines · 34 tokens per session scan A 67c4677005e2

Subscribe to this mod's changes

trace-matrix is a skill published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 2,280 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 2026-09-25.

Backend and APIs Databases lidar radar road-safety street-safety traffic-analysis urban-analytics

trace-matrix next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
trace-matrixbanshee-data/velocity.report	Skill	11	today	Apache-2.0	A	34	Claude Code
event-store-designwshobson/agents	Skill	42k	yesterday	MIT	A	33	Claude Code
platform-custom-field-generateforcedotcom/sf-skills	Skill	1.1k	2d ago	Apache-2.0	A	139	Claude Code
field-service-sobject-create-configureforcedotcom/sf-skills	Skill	1.1k	2d ago	Apache-2.0	A	74	Claude Code
durable-objectsfcakyon/claude-codex-settings	Skill	1.2k	yesterday	Apache-2.0	A	22	Claude Code
nornicdb-grpcorneryd/NornicDB	Skill	923	yesterday	MIT	A	98	Claude Code, Codex
firebaseericrisco/rsc-harness	Skill	503	2d ago	MIT	A	77	Claude Code, Codex

velocity.report: Skill for Claude Code