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/detect-tasknpx skills add restarter/lets-workflow --skill detect-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 | $0.00041 | $0.02920 |
| Opus 5 | $0.00020 | $0.01460 |
| Sonnet 5 | $0.00008 | $0.00584 |
| Haiku 4.5 | $0.00004 | $0.00292 |
Grade A, and why
detect-task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detect Active Task
Parse the task-state file / current git branch to find the active task ID (tracker-adapter-aware). Used by commands that need to know which task is in progress.
IMPORTANT: If the spec below invokes any deferred tool (e.g.
AskUserQuestion), you MUST load and call it as specified. Never skip the call, never substitute a default answer of your own — the tool invocation is part of the contract. This is critical.
Why This Exists
10+ commands need to detect the active task from branch name. This skill centralizes the logic so branch format changes are updated in one place.
Detection Flow
Step 1: Parse Branch Name
BRANCH=$(git branch --show-current)
Extract the task ID from the branch name. Formats:
feature/<task-id>-<slug>- standard LETS branches (main repo)worktree-<task-id>-<slug>- worktree branches created via/lets:worktree createin new-branch mode (the LETS convention)worktree-<custom-name>- worktree branch without an embedded task ID; use fallback- any other shape (e.g.
feature/foo,bugfix/bar) - attached existing branch via/lets:worktree create --attach; no task ID in the name; use fallback
The <task-id> shape is TRACKER-DEPENDENT (the id sits immediately after feature/ or worktree-, up to the first -<slug> boundary):
- beads:
<prefix>-<alphanum>[.<number>]- e.g.lets-abc,lets-abc.1,proj-xyz.42 - a numeric-id tracker: a pure-numeric id - e.g.
48647, sofeature/48647-<slug> - other adapters: the tracker's own id shape
Do NOT apply the beads <prefix>-<alphanum> regex on a non-beads project - it false-positives on a slug word: feature/48647-lifecycle-test makes the beads regex capture lifecycle-test, NOT the numeric id 48647. Match using the ACTIVE tracker's id shape ({LETS_TRACKER} from LETS Config). When the branch shape is ambiguous, the .task-<slug> file (Step 1.5, authoritative) and the Step 2 search-and-confirm fallback are safer than a branch-name guess.
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 · 131 lines · 41 tokens per session scan A 8d0346ed08d8
detect-task is a skill published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 9d ago), licensed MIT. It adds 41 tokens to every session and 2,920 once invoked, about $0.0002 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…