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-all-tasks)<a href="https://agentmods.dev/skills/motlin/claude-code-plugins/do-all-tasks"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/do-all-tasks/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-all-tasks"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/do-all-tasks.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 | $0.00044 | $0.01299 |
| Opus 5.5 | $0.00018 | $0.00520 |
| Sonnet 5.5 | $0.00009 | $0.00260 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
do-all-tasks 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Do All Tasks
Work through incomplete tasks in .llm/todo.md, one fresh worker and one commit per 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-all-tasks/SKILL.md file.
Instructions the user gave after the skill name govern how far the loop runs and any constraints on it. Without instructions, run until no incomplete tasks remain.
Leave Plan Mode First
Workers make live edits, so this workflow cannot run in plan mode. If plan mode is active in Claude Code, call ExitPlanMode before doing anything else.
Check Delegation Before Starting
Before running any queue script, confirm the session exposes callable tools to spawn a fresh subagent and wait for its result. In Codex, check the available tool set rather than assuming delegation is supported.
If either capability is missing, stop. Report which one is unavailable and that this workflow needs both. Leave task states, archives, and Git unchanged, and do not mark tasks blocked for this reason. Implementing tasks directly in the leader is not a fallback.
Keep the Leader Focused
The leader (this agent) coordinates and never implements. It uses only Bash and the agent-spawning tool, never Read, Edit, Write, Grep, or Glob. With Bash it may only:
- Extract work with
task_get.py, including--index,--range, or--limitto preview the queue beyond the next task. - Survey blocked work with
task_unblock.py --dry-run. - Record a failed attempt with
task_mark.py --marker='!' --reason='<what failed>', adding--title '<task title>'when the failed task is not the first incomplete one. - Inspect Git status and commit boundaries.
- Run the test gate against
HEAD. - Archive the task list with
task_archive.py.
task_get.py is the leader's only view of the queue. It never reads .llm/todo.md, task-referenced files, or source files. Each worker discovers its own implementation context.
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 4cb6828360e6
- 22d ago Changed · -22 lines · -1 tokens per session ea7f70b08c5c
- 1mo ago First seen · 124 lines · 45 tokens per session scan A dc191fec9e10
do-all-tasks is a skill published in the GitHub repository motlin/claude-code-plugins (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 1,299 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
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…
remove
Remove a deployed framework or addon from the current workspace.