Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add motlin/claude-code-plugins/plugin install markdown-tasksWrote 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.
[](https://agentmods.dev/skills/motlin/claude-code-plugins/do-one-task)<a href="https://agentmods.dev/skills/motlin/claude-code-plugins/do-one-task"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/do-one-task/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/motlin/claude-code-plugins/do-one-task"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/do-one-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.00448 |
| Opus 5.5 | $0.00017 | $0.00179 |
| Sonnet 5.5 | $0.00008 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
do-one-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 9d 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.
What it actually says
Do One Task
Use the markdown-tasks:tasks skill for script path rules and task semantics. <plugin-root> is ${CLAUDE_PLUGIN_ROOT} in Claude Code; in Codex, it is the plugin root that contains this skills/do-one-task/SKILL.md file.
Extract the next task:
python <plugin-root>/scripts/task_get.py .llm/todo.md
If no task is returned, report that there are no incomplete tasks.
Implement only the extracted task. Ignore unrelated TODO/TASK comments in source code.
Run appropriate tests and validation, then complete the repository's finish workflow so the task has its own commit, precommit passes against that commit, and the branch is rebased when required. When the build, git, and orchestration plugins are installed, use the build:precommit, git:commit, git:git-rebase, and orchestration:finish skills; in Claude Code, /orchestration:finish runs the full pipeline. Commit before running git test run HEAD, which refuses a dirty tree.
The task must end as exactly one new commit. Finish can leave a cleanup fixup! commit on top of the task commit, so after it returns, check the commits between the rebase target (${UPSTREAM_REMOTE:-upstream}/${UPSTREAM_BRANCH:-main}) and HEAD for fixup! commits and fold any into the task commit with the git:git-rebase skill, which autosquashes. Run precommit again if the squash changed HEAD.
Mark the task complete only after implementation, commit, and validation succeed:
python <plugin-root>/scripts/task_mark.py .llm/todo.md
If implementation or validation fails, leave the task incomplete and report the failure. The markdown-tasks:do-all-tasks leader marks failed attempts [!].
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.
- 9d ago Changed · +2 lines d6fabc37efe4
- 22d ago Changed · -7 lines b55f5ca4d7b3
- 1mo ago First seen · 36 lines · 42 tokens per session scan A fdbaa1c047a0
do-one-task is a skill published in the GitHub repository motlin/claude-code-plugins (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 448 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
gsd-quick-batch
Batch several /skill:gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-pause-work
Create context handoff when pausing work mid-phase.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
gait-session-tracking
GAIT session lifecycle management - branch creation, turn recording, audit logging for every NetClaw operation. Use when starting a new NetClaw session, recording a health check or config change, pinning a pre-change baseline, or viewing the audit trail for a troubleshooting session.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.