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 commands/evan043/claude-cli-advanced-starter-pack/github-task-start.templategit clone --depth 1 https://github.com/evan043/claude-cli-advanced-starter-packWhat 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 | $0.00000 | $0.00972 |
| Opus 5 | $0.00000 | $0.00486 |
| Sonnet 5 | $0.00000 | $0.00194 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade A, and why
github-task-start.template 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 2d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Runtime Compatibility
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows:
AskUserQuestion=> ask the user directly in chat.WebSearch/WebFetch=> use available web tools (search_query,open,find) and cite links.Read/Write=> use shell/filesystem tools in this workspace.- Claude-only MCP calls (for example Playwright MCP names) => use available equivalents or clearly state fallback.
- Keep intent and output format identical; only adapt execution mechanics.
description: Start or complete a task from GitHub Project Board model: sonnet
/github-task-start - Start GitHub Task
Start working on a task from your GitHub Project Board or mark it complete.
{{#if versionControl.projectBoard.number}}
Usage
/github-task-start <issue-number> # Start working on issue
/github-task-start <issue-number> --complete # Complete the issue
Workflow
Starting a Task
-
Fetch Issue Details
gh issue view <number> --repo {{versionControl.owner}}/{{versionControl.repo}} --json title,body,labels,assignees -
Create Branch (optional)
git checkout -b feature/<issue-number>-<slug> -
Update Project Board Status
# Move to "In Progress" status gh project item-edit --id <item-id> --project-id {{versionControl.projectBoard.id}} --field-id <status-field-id> --single-select-option-id <in-progress-id> -
Create Task List
- Analyze issue requirements
- Create TodoWrite tasks based on acceptance criteria
- Begin implementation
Completing a Task
-
Verify All Tests Pass
{{#if testing.e2e.testCommand}} {{testing.e2e.testCommand}} {{else}} npm test {{/if}} -
Create Commit
git add . git commit -m "feat: <description> Closes #<issue-number>" -
Create PR
gh pr create --title "<title>" --body "Closes #<issue-number>" --repo {{versionControl.owner}}/{{versionControl.repo}}
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.
- 2d ago First seen · 133 lines · 0 tokens per session scan A f988781c90d1
github-task-start.template is a command published in the GitHub repository evan043/claude-cli-advanced-starter-pack (61 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 972 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.
Other commands, from other repositories
build-agent
Build an AI agent on Cloudflare using the Agents SDK.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
snapshot
Capture screenshot + DOM tree + page state + storage in one shot.
storage
Inspect localStorage, sessionStorage, and cookies from the Tauri webview. One-shot read — no writes.
eval
Evaluate a JavaScript expression in the Tauri app's webview.
van
Command "van" from vanzan01/claude-code-sub-agent-collective, covering /van - collective routing engine, 🎯 purpose - smart routing, 🚐 routing flow, 🚀 dual-mode routing protocol and 🧠 immediate agent routing.