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 skills add JakubMikolajek/codex-skills-collection --skill task-analysisgit clone --depth 1 https://github.com/JakubMikolajek/codex-skills-collectionWrote 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/jakubmikolajek/codex-skills-collection/task-analysis)<a href="https://agentmods.dev/skills/jakubmikolajek/codex-skills-collection/task-analysis"><img src="https://agentmods.dev/badge/skills/jakubmikolajek/codex-skills-collection/task-analysis/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/jakubmikolajek/codex-skills-collection/task-analysis"><img src="https://agentmods.dev/badge/skills/jakubmikolajek/codex-skills-collection/task-analysis.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 | $0.00053 | $0.00654 |
| Opus 5 | $0.00026 | $0.00327 |
| Sonnet 5 | $0.00011 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
task-analysis 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Analysis
This skill helps you gather and expand context about a specific task to be developed, looks for gaps in the task description and helps to understand the current state of the system.
Task analysis process
Use the checklist below and track your progress:
Analysis progress:
- [ ] Step 0: Determine input source
- [ ] Step 1: Gather context from local sources
- [ ] Step 2: Gather information from repository artifacts
- [ ] Step 3: Identify gaps and ask clarification questions
- [ ] Step 4: Based on the answers and gathered information finalize the research report
Step 0: Determine input source
Before gathering information, determine how the task context was provided:
- Research & plan files exist (
*.research.md,*.plan.md): Read them as the primary source of requirements, acceptance criteria, scope, and definition of done. - Context provided directly in the prompt: Extract requirements, acceptance criteria, and scope from the user's message. Treat the prompt as the single source of truth. If critical information is missing, ask for clarification before proceeding.
- Local project artifacts available: Use local markdown docs, ADRs, tickets mirrored in files, and code comments as additional context.
This determination affects how much of Steps 1–2 you need to execute. If context is already fully provided inline or in local files, skip redundant discovery.
Step 1: Gather context from local sources
Collect all available local context first:
- Existing research and plan files
- Local docs in
docs/,README*, ADRs, and architecture notes - Open TODOs, comments, and implementation notes in the codebase
Do not assume external task management tools are available.
Step 2: Gather information from repository artifacts
Analyze the codebase based on task requirements. Identify modules, files, and flows related to the task domain. When links are provided in task context, only use them if they are directly accessible from the current environment. Prefer local, verifiable sources over assumptions.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 62 lines · 53 tokens per session scan A 265cf966171a
task-analysis is a skill published in the GitHub repository JakubMikolajek/codex-skills-collection (5 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 654 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…