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 skills/restarter/lets-workflow/take-tasknpx skills add restarter/lets-workflow --skill take-taskgit clone --depth 1 https://github.com/restarter/lets-workflowWhat 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 | $0.00076 | $0.02371 |
| Opus 5 | $0.00038 | $0.01185 |
| Sonnet 5 | $0.00015 | $0.00474 |
| Haiku 4.5 | $0.00008 | $0.00237 |
Grade A, and why
take-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 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Take Task
Claim a tracker task and prepare the working environment.
IMPORTANT: If the spec below invokes any deferred tool (e.g.
AskUserQuestion), you MUST load and call it as specified. Never skip the call, never substitute a default answer of your own — the tool invocation is part of the contract. This is critical.
Why This Exists
Multiple flows need "claim task + prepare branch": /lets:start, mid-session task switch, direct "візьми таск X". Centralizing ensures consistent branch naming, worktree handling, and session ref saving.
Flow
Step 1: Resolve Task
show task=<task-id>
Verify task exists. Then claim it (set-status is a state change - HARD-FAIL loud if the binding can't run; do NOT proceed to branch setup on a failed claim):
set-status task=<task-id> status=in_progress
Step 2: Check Uncommitted Changes
Before switching branches, check for uncommitted changes:
git status --short
If changes exist and branch switch is needed, ask user:
AskUserQuestion(
questions=[{
question: "Uncommitted changes on current branch. What to do?",
header: "Uncommitted",
options: [
{ label: "Stash", description: "git stash, switch branch, remind to pop later" },
{ label: "Commit first", description: "Commit changes, then switch branch" },
{ label: "Stay", description: "Skip branch switch - work on current branch" }
],
multiSelect: false
}]
)
Handle response:
- Stash ->
git stash, proceed with branch switch, remind togit stash poplater - Commit first -> delegate to commit skill, then proceed with branch switch
- Stay -> skip branch switch, warn about mixed work, then continue to Step 5 (the task was already claimed in Step 1 - save its
.taskstate file for the current branch; do NOT stop before it, or detect-task//lets:doneare left with a claim but no boundary file).
If staying on current branch (worktree, already correct) or no changes - skip this step.
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 · 203 lines · 76 tokens per session scan A b92c403899c3
take-task is a skill published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 9d ago), licensed MIT. It adds 76 tokens to every session and 2,371 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…