do-task

do-task is a skill for Claude Code, Codex from samsantosb/ship-it. It costs 76 tokens per session (1,704 once invoked), scanned A, original, MIT.

A workflow skill that takes a development task card from pickup through implementation, validation, pull request creation, and review watching. A pull request is a proposed code change submitted for review.

In plain words
What is it for?
Use it when you want an agent to execute a defined task end to end. It helps implement changes, validate them, open and label a pull request, and continue through review.
Why use it?
It gathers the work into one repeatable flow, so implementation, checks, review, and notifications are not handled as separate manual steps. It follows the project's written guidelines and task contract.

Skill for Claude CodeCodex

Part of the ship-it plugin — 7 skills shipped together

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/samsantosb/ship-it/do-task
Any agent
npx skills add samsantosb/ship-it --skill do-task
Clone the repo
git clone --depth 1 https://github.com/samsantosb/ship-it

Made for: Claude Code, Codex.

Or install ship-it, the plugin that ships this one along with the rest of its 7 skills.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,704 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 $0.00076 $0.01704
Opus 5 $0.00038 $0.00852
Sonnet 5 $0.00015 $0.00341
Haiku 4.5 $0.00008 $0.00170

Measured 3d ago against content hash 0625d8bb2890, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

do-task 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 3d 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/do-task/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: do-task

Executes one card through the full cycle. Thin orchestrator: the card supplies the contract, the guidelines supply the rules, pr-flow supplies the PR mechanics, watch-pr supplies the review cycle. Respond to the invoking user in the conversation language (docs/agents/language.md; unset → their language); team-visible surfaces follow language: in docs/agents/tracker.md.

Load before acting: ${CLAUDE_PLUGIN_ROOT}/shared/workflow-context.md, ${CLAUDE_PLUGIN_ROOT}/shared/card-format.md, ${CLAUDE_PLUGIN_ROOT}/shared/pr-flow.md, ${CLAUDE_PLUGIN_ROOT}/shared/autonomy.md, and ${CLAUDE_PLUGIN_ROOT}/shared/guardrails.md — this skill writes code, commits and pushes; the loading contract applies in full.

Automode contract

Invoking /do-task authorizes the complete flow: pickup → implement → validate → PR → labels → /watch-pr → notification. No "may I proceed?" — ever. The escalation points listed at the bottom are the only stops, and each follows the park protocol (autonomy.md): persist, notify with the exact question + resume command, exit cleanly. A parked run is a successful run.

Step 0 — Resolve and parse

  • Roles per workflow-context (config first, then detection/defaults — a role that would need a question in an unattended run falls to its default and is recorded in the trace).
  • Argument: card path (tasks/TASK-007.md), bare id (resolved via INDEX/tracker), or tracker URL (URL pins the tracker). Empty argument → list the unblocked todo cards and stop — choosing what to work on is the human's call, not automode's.

Step 1 — Pickup (the lock)

  1. Read the card. It must be todo/ready-for-agent, not parked, with every blocked_by target done/closed — any open blocker → park (this is the #1 fleet collision).
  2. Re-verify state immediately before transitioning (card-format § Concurrency). Mode B mechanics spelled out: read the assignee field right before setting it — already claimed by anyone → stop, another agent owns it; only an empty assignee may be taken.
  3. Transition todo → in-progress per the lifecycle table.
  4. Resume case: card already in-progress with our branch existing (branch name = card id) → resume from the branch's state, never restart or duplicate. How to reconstruct progress: run the card's Test criteria — the test results are the checkpoint (green = that slice is done; red/missing = resume there). Dirty working tree → inspect the in-flight diff and finish or commit it first; never stash away or discard work. in-progress by someone else (different assignee/branch) → stop and say so — not our card.

Read the full file on GitHub · 81 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. 3d ago First seen · 81 lines · 76 tokens per session scan A 0625d8bb2890

Subscribe to this mod's changes

do-task is a skill published in the GitHub repository samsantosb/ship-it (22 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,704 once invoked, about $0.0004 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

release

Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.

openai/symphony · 42 tokens

release-notes

Draft concise release notes.

ollama/ollama · 9 tokens

greptimedb-release

Runbook for publishing a new GreptimeDB version (tag + GitHub release + docs release-note PR) on the upstream GreptimeTeam/greptimedb repo. Use when asked to "release" / "publish" a GreptimeDB version (e.g. v1.1.0, v1.0.3).

GreptimeTeam/greptimedb · 75 tokens

refresh-arm-sdk-release

WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…

Azure/azure-sdk-for-net · 91 tokens

store-update

在 CCX Desktop 发布后下载 Store MSIX 并生成发布公告。用户提到 Store 上架、MSIX、从 GitHub Release 下载 store.msix、发布后同步 Windows Store、从 release 填写商店更新内容时必须使用此技能。该技能会下载最新 GitHub Release 的 amd64/arm64 MSIX,校验 sha256,从 Release body 生成 Store listing releaseNotes 预览,并输出手动上传指引。.

BenedictKing/ccx · 100 tokens

publish-registry

Publish @agentos-software/ registry packages from AgentOS. Use whenever the user asks to publish or release registry software/agent packages.

rivet-dev/agentos · 32 tokens