task-start

A task-start procedure for GitHub-based projects that prepares the repository, work branch, task board, and planning template before work begins.

In plain words
What is it for?
Use it when starting an approved GitHub issue to check the issue, update the base branch, create a task branch or worktree, update the daily board, and write the task plan.
Why use it?
It reduces setup mistakes and makes the starting state of a task visible to the team.

Skill for Claude CodeCodex

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/postmelee/hyper-waterfall/task-start
Any agent
npx skills add postmelee/hyper-waterfall --skill task-start
Clone the repo
git clone --depth 1 https://github.com/postmelee/hyper-waterfall

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 706 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 $0.00053 $0.00706
Opus 5 $0.00026 $0.00353
Sonnet 5 $0.00011 $0.00141
Haiku 4.5 $0.00005 $0.00071

Measured 2d ago against content hash e0ef4f76b146, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-start 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.

templates/locales/en/mydocs/skills/task-start/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hyper-Waterfall Task Start

Trigger

  • The task requester explicitly says "start Issue #N" or "proceed with task #N."
  • The task requester invokes this SKILL directly.

Preconditions

  • An approved Issue number and milestone exist.
  • The target repository working tree is clean, or a separate worktree decision has been made.
  • gh CLI is authenticated for the current user.

Procedure

  1. Confirm Issue information.
    gh issue view {N} --json number,title,milestone,state,body
    
  2. Update {BASE_BRANCH}.
    git fetch origin
    git checkout {BASE_BRANCH}
    git pull --ff-only
    
  3. Create the work branch. If another worker is using the main worktree, use a separate worktree.
    # single worktree
    git checkout -b local/task{N}
    
    # separate worktree, recommended to avoid interfering with another agent
    git worktree add ../{repo}-task{N} -b local/task{N} origin/{BASE_BRANCH}
    
  4. Update daily task board: add a row to mydocs/orders/{yyyymmdd}.md.
    • Use output format from mydocs/_templates/orders.md.
    • Row format: | #{N} | {task title} | In progress | M{milestone}, task plan written and awaiting approval |
    • Place it under the appropriate milestone section. Use "Common - Operations" for operational work.
  5. Create task plan: mydocs/plans/task_m{milestone}_{N}.md.
    • Use central template mydocs/_templates/task_plan.md.
    • Only if the template cannot be read, use these fallback sections: purpose / background / scope included and excluded / design direction / expected changed files / tentative stages of 3-6 stages / verification plan / risks / approval request.
  6. Verify changes.
    git status --short
    git diff --check
    
  7. Commit once.
    git add mydocs/plans/task_m{milestone}_{N}.md mydocs/orders/{yyyymmdd}.md
    git commit -m "Task #{N}: task plan and daily task board update"
    
  8. Request task plan approval from the task requester.

Verification

  • git log --oneline -1 shows Task #{N}: task plan and daily task board update.
  • mydocs/orders/{yyyymmdd}.md contains a #{N} row.
  • mydocs/plans/task_m{milestone}_{N}.md fills required sections from mydocs/_templates/task_plan.md.

Read the full file on GitHub · 78 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. 2d ago First seen · 78 lines · 53 tokens per session scan A e0ef4f76b146

Subscribe to this mod's changes

task-start is a skill published in the GitHub repository postmelee/hyper-waterfall (78 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 706 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.

Related

Other skills, from other repositories

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

harness

하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시, (3) 새로운 도메인/프로젝트에 대한 하네스 기반 자동화 체계를 구축할 때, (4) 하네스 구성을 재구성하거나 확장할 때, (5) '하네스 점검', '하네스 감사', '하네스 현황', '에이전트/스킬 동기화' 등 기존 하네스 운영/유지보수 요청 시 사용.

revfactory/harness · 170 tokens

pr-review

Review a GitHub pull request and post a verdict comment. Stateful — if a previous review comment exists, review only the new commits since the last review and track whether prior findings were addressed. Focus on code cleanliness, duplication, and docs sync. Use when user says "review this PR", "check the PR", "leave…

lee-to/aif-handoff · 83 tokens

new-plugin

Factory line for adding a new HAR verification plugin (like playwright or rocketsim) for any framework — research the framework docs, build the template under src/templates/plugins/, register it everywhere, validate on a real repository, and open a PR. Use when asked to add/create a plugin, plugin template, or…

os-factory/har · 89 tokens

factory-line

Factory line for executing one station of a declared multi-station program — read the installed line bundle (har line status), plan parallel work into isolated HAR slots, run the cumulative gate with har line gate, and hand off for human review. Use when asked to "run a factory line", "run the next station", "execute…

os-factory/har · 101 tokens

v1-milestone

Factory line for executing one milestone of the HAR v1.0.0 refactor (epic os-factory/har#225) — plan the wave of parallel subagents, implement each issue in its own HAR slot, ship stacked PRs, run the fixture-e2e milestone gate, and hand off for review. Use when asked to "run the next v1 milestone", "work on v1.0.0"…

os-factory/har · 110 tokens