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/strvcom/flutter-template/implement-tasks-sequencenpx skills add strvcom/flutter-template --skill implement-tasks-sequencegit clone --depth 1 https://github.com/strvcom/flutter-templateWhat 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 | $0.00114 | $0.00901 |
| Opus 5 | $0.00057 | $0.00451 |
| Sonnet 5 | $0.00023 | $0.00180 |
| Haiku 4.5 | $0.00011 | $0.00090 |
Grade A, and why
implement-tasks-sequence 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Tasks Sequence
Orchestrate the full implementation of a feature by executing all tasks from a task list using an
agent team. The flow runs uninterrupted — no per-task builds, no per-task tests, no commits, and
no final verification. Verification is the caller's responsibility (normally /start-job, which
runs build-verify and then pr-review uncommitted after this skill completes).
Step 1: Load the Task List
Read .claude/tasks/[feature-name]/tasks.md to understand:
- All tasks and their phases
- The dependency graph
- Which tasks can run in parallel vs. which must be sequential
Step 2: Plan Execution Order
Build an execution plan from the dependency graph:
- Group tasks into waves — each wave contains tasks whose dependencies are all satisfied by prior waves.
- Tasks within the same wave that have no mutual dependencies can be dispatched to agents in parallel.
- Tasks that depend on a previous task must wait for it to complete.
Briefly summarize the execution plan (wave count, parallel groups) and proceed — no approval needed.
Step 3: Execute Each Wave
For each wave, dispatch tasks to agents:
Per-Task Agent Instructions
Each agent receives:
- The task file (
.claude/tasks/[feature-name]/[num]_task.md) - The PRD (
.claude/tasks/[feature-name]/prd.md) - The Tech Spec (
.claude/tasks/[feature-name]/techspec.md) - Instructions to follow the
/implementskill workflow for coding conventions and applicable skills — BUT skip all build, test, lint, and commit steps. Only source code changes should be made. Verification is centralized at the end of the sequence.
Explicitly tell each agent:
Do NOT run builds, do NOT run tests, do NOT run lint-format, do NOT commit. Only write the code changes for your assigned task. Verification and commit decisions happen at the end of the overall flow.
Wave Completion Gate
A wave is complete when all tasks in the wave have finished writing their code changes. Since there is no per-task verification, the gate is just task completion. Do not start the next wave until the current wave's agents have all returned.
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 · 82 lines · 114 tokens per session scan A ae5288912d35
implement-tasks-sequence is a skill published in the GitHub repository strvcom/flutter-template (24 stars, last pushed 2mo ago), licensed MIT. It adds 114 tokens to every session and 901 once invoked, about $0.0006 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…