tracker-routing

tracker-routing is a skill for Claude Code, Codex from salavender/antigravity-compound-engineering-plugin. It costs 0 tokens per session (655 once invoked), scanned A, original, MIT.

A routing guide for deciding whether information belongs in GitHub, Linear, or the repository. GitHub tracks engineering work, while Linear tracks temporary decisions and requests for human attention.

In plain words
What is it for?
Use it when deciding where to record specifications, issues, pull requests, architecture choices, risks, or approval gates.
Why use it?
It prevents duplicate project-management records and keeps each kind of information where its meaning is preserved.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/salavender/antigravity-compound-engineering-plugin/tracker-routing
Any agent
npx skills add salavender/antigravity-compound-engineering-plugin --skill tracker-routing
Clone the repo
git clone --depth 1 https://github.com/salavender/antigravity-compound-engineering-plugin

Made for: Claude Code, Codex.

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 tracker-routing

README.md
[![agentmods](https://agentmods.dev/badge/skills/salavender/antigravity-compound-engineering-plugin/tracker-routing.svg)](https://agentmods.dev/skills/salavender/antigravity-compound-engineering-plugin/tracker-routing)
Your own site
<a href="https://agentmods.dev/skills/salavender/antigravity-compound-engineering-plugin/tracker-routing"><img src="https://agentmods.dev/badge/skills/salavender/antigravity-compound-engineering-plugin/tracker-routing.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 655 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 5.1 $0.00000 $0.00655
Opus 5 $0.00000 $0.00328
Sonnet 5 $0.00000 $0.00131
Haiku 4.5 $0.00000 $0.00065

Measured 6d ago against content hash 2a3023174d0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tracker-routing 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 6d 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.

skills/tracker-routing/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tracker Routing: Linear vs GitHub

Purpose

Route work to the surface that owns its semantic state. Do not create a second project-management layer.

Canonical boundaries

Git docs/specs/ADRs  = durable truth
GitHub Issues/PRs    = engineering execution + evidence
Linear               = temporary attention, brainstorming, decisions, gates

Before creating work

Ask:

  1. Is this durable knowledge? Write it in the repository.
  2. Is this executable engineering work? Use GitHub Issues/PRs.
  3. Is this collaborative reasoning, a business/architecture decision, risk acceptance, or a human gate? Use Linear.
  4. Does an existing object already cover it?
  5. Will the object still have value after the canonical Git record exists?

Do not create a Linear issue for every backlog row, probe, log, CI result, or engineering subtask. Do not create a GitHub issue for pure brainstorming.

Linear

Use Linear for:

  • product/strategy questions
  • architecture alternatives
  • hypothesis comparison
  • business/risk decisions
  • go/no-go gates
  • operator attention that requires human action
  • temporary multi-agent reasoning

Keep the issue thin. Link to Git documents. Never paste the plan/spec/research body.

When the decision is made:

  1. write the durable conclusion to Git (docs/decisions, docs/specs, or the relevant canonical doc);
  2. link any resulting GitHub execution work;
  3. archive the Linear object when it is no longer an active decision/attention surface.

Auto-synced GitHub projections

If Linear's GitHub Issues Sync creates a GitHub issue for a Linear decision, that GitHub issue is a read-only projection, not engineering work.

  • Do not implement it.
  • Do not assign engineering agents to it.
  • Do not create a branch/PR from it.
  • Do not close it independently of the Linear decision while Issues Sync is enabled.
  • Prefer disabling GitHub Issues Sync for this repository; keep PR/commit linking enabled.

GitHub

Engineering agents default to GitHub for:

Read the full file on GitHub · 96 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. 6d ago First seen · 96 lines · 0 tokens per session scan A 2a3023174d0c

Subscribe to this mod's changes

tracker-routing is a skill published in the GitHub repository salavender/antigravity-compound-engineering-plugin (47 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 655 tokens. 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens