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/jonathanung/finesse/task-workflowsnpx skills add jonathanung/finesse --skill task-workflowsgit clone --depth 1 https://github.com/jonathanung/finesseWhat 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 | $0.00027 | $0.06579 |
| Opus 5 | $0.00014 | $0.03290 |
| Sonnet 5 | $0.00005 | $0.01316 |
| Haiku 4.5 | $0.00003 | $0.00658 |
Grade A, and why
task-workflows 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 — 589 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Workflows
After detecting the task type, follow the corresponding workflow below. Every workflow ends with plan construction, validation, pre-flight, and presentation. The phases before that differ by task type.
UAT Checkpoints
Phases marked with [UAT] require a User Acceptance Testing checkpoint as defined in the main command (finesse.md). When you complete a [UAT] phase, follow the UAT Checkpoint Procedure before proceeding to the next phase.
If the user has elected to fast-forward UAT (by selecting "Accept and skip remaining UAT" at any checkpoint), skip the checkpoint and proceed directly. Discovery/Understanding phase confirmations are never affected by fast-forward.
Task Type Detection
Classify the user's task into one of these types based on their description:
| Type | Signals |
|---|---|
| feature | "Add", "build", "create", "implement", "new", introduces new functionality |
| bugfix | "Fix", "broken", "not working", "error", "crash", "wrong", "regression" |
| refactor | "Refactor", "clean up", "reorganize", "restructure", "improve code", "tech debt" |
| testing | "Add tests", "test coverage", "write tests", "validate", "QA" |
| performance | "Slow", "optimize", "performance", "speed up", "bottleneck", "latency" |
| research | "Research", "investigate", "compare", "evaluate", "analyze", "study", "survey", "document", "explore options", "understand", "assessment", "trade-offs", "pros and cons", "spike", "feasibility" |
If ambiguous, ask the user. Do not guess.
Scope Analysis & Decomposition Framework
After exploration reveals codebase context but before architecture/strategy design, analyze whether the task should be decomposed into multiple independent sub-workflows that each run as a separate ralph-loop.
Decomposition Triggers
Propose splitting when ANY of these apply:
- Estimated iteration count exceeds 25 (the ralph-loop ceiling)
- Task touches more than 2 independent functional areas with no shared state
- Task contains sub-tasks with no mutual dependencies
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 · 589 lines · 27 tokens per session scan A dfc0b700fe2a
task-workflows is a skill published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 27 tokens to every session and 6,579 once invoked, about $0.0001 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 2026-08-31.
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…