Chalk Labs
Need help deploying tracker-routing?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/salavender-tracker-routing
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
tracker-routing- Description
- None
- License
- MIT
- Instructions
- 96 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- missing YAML frontmatter
- name: missing
- description: missing
Files (1)
- SKILL.md
SKILL.md (first lines)
# 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 ```text 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: - implementation - bugs and refactors - tests - security remediation - performance work - CI/CD - deployment verification - code review - scanner findings Keep implementation details, PR discussion, review verdicts, and CI evidence in GitHub. If work originated from Linear, put `Linear: SAL-NNN` in the GitHub issue/PR and link the canonical spec/ADR. Do not copy the Linear discussion. ## Escalation GitHub → Linear only when engineering discovers a question requiring human/business/architecture/risk adjudication. Linear → GitHub only when a decision creates executable engineering work. This is promotion, not synchronization. ## Completion ```text canonical Git truth updated → GitHub execution merged/verified → Linear gate updated if needed → Linear archived when no longer active ``` ## Capacity Linear Free has a 250-unarchived-issue ceiling. Protect capacity by keeping the Linear working set small. Archive completed decision/attention objects promptly; do not delete valuable history merely to make the counter smaller.
From salavender/antigravity-compound-engineering-plugin, MIT.
More from salavender/antigravity-compound-engineering-plugin
- 0.497score
git-workflow
salavender
Standardized patterns for Git branching, worktrees, and lifecycle management.
SkillDFreshness: D★ 48Claude Code +9 - 0.497score
react-hooks
salavender
Resolves React hook violations (rules of hooks, useEffect dependencies, hook ordering).
SkillDFreshness: D★ 48Claude Code +9 - 0.497score
standard-security-auth
salavender
Security & Authentication Specialist - Expert in JWT, cookie-based auth, MFA, and generic security patterns
SkillDFreshness: D★ 48Claude Code +9 - 0.492score
mobile
salavender
Expertise in mobile responsiveness, specifically table patterns and standard UI component styling.
SkillDFreshness: D★ 48Claude Code +9
Signals
- Stars
- 48
- Forks
- 7
- Open issues
- 1
- Last commit (this folder)
- Aug 14, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from salavender
- 0.497score
git-workflow
salavender
Standardized patterns for Git branching, worktrees, and lifecycle management.
SkillDFreshness: D★ 48Claude Code +9 - 0.497score
react-hooks
salavender
Resolves React hook violations (rules of hooks, useEffect dependencies, hook ordering).
SkillDFreshness: D★ 48Claude Code +9 - 0.497score
standard-security-auth
salavender
Security & Authentication Specialist - Expert in JWT, cookie-based auth, MFA, and generic security patterns
SkillDFreshness: D★ 48Claude Code +9 - 0.492score
mobile
salavender
Expertise in mobile responsiveness, specifically table patterns and standard UI component styling.
SkillDFreshness: D★ 48Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get tracker-routing running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
tracker-routing skill. Agent Mart. https://agentmart.dev/skills/salavender-tracker-routing (last updated 2026-10-24)