Borrowing it
Nothing to install: this file belongs to yusifeng/formax. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yusifeng/formax/main/.codex/skills/analyze-task/SKILL.mdgit clone --depth 1 https://github.com/yusifeng/formaxWrote 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/yusifeng/formax/analyze-task)<a href="https://agentmods.dev/skills/yusifeng/formax/analyze-task"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/analyze-task/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/yusifeng/formax/analyze-task"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/analyze-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.01073 |
| Opus 5.5 | $0.00022 | $0.00429 |
| Sonnet 5.5 | $0.00011 | $0.00215 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
analyze-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 2mo 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Task
Use this skill before coding for non-trivial repository work:
- new features
- cross-layer changes
- architecture or model changes
- complex bugs
- tasks that likely need multiple commits / reviews / loops
Do not use it for tiny local edits that can be implemented and verified immediately.
Purpose
Produce a short Analysis Brief that makes the task discussable and executable.
This skill is for:
- clarifying the goal
- defining non-goals
- identifying what must be decided before coding
- deciding whether a subagent is justified
- preparing the task for a scope-alignment discussion
- setting up the handoff to
write-task-todoonly after alignment
This skill is not for writing code and not for writing docs/todolist.md.
Core rules
-
Prioritize structure before UI
- think about canonical docs/contracts, data model, types, interfaces, repo/service/runtime boundaries before UI details
-
Prefer explicit boundaries
- say what is in scope and what is not
- surface ambiguity instead of silently choosing
-
Use subagents selectively
- default is local analysis
- use an
xhighexplorer subagent only when the task is cross-layer, ambiguous, high-risk, or likely to benefit from an independent architectural read - if you use a subagent, give it a narrow question; do not outsource the entire solution
-
Do not create a canonical doc yet unless the concept is already clearly stable and long-lived
- early definitions belong in analysis/todo first
-
Every analysis should end with an alignment state:
- ready for alignment discussion
- ready for
write-task-todoafter confirmation - or blocked on a single clarification
Required output
Produce a brief with these sections:
## Analysis Brief
### Goal
### Product Boundary
### Scope
### Non-goals
### Canonical-Doc Impact
### Data / Type / Interface First
### Layer Impact
### Risks / Ambiguities
### Need Subagent?
### Test Strategy
### Alignment Questions
### Ready for Todo?
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.
- 2mo ago First seen · 164 lines · 55 tokens per session scan A d19e2a829053
analyze-task is a skill published in the GitHub repository yusifeng/formax (184 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 1,073 once invoked, about $0.0002 per session on Opus 5.5. 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.
analyze-task compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| analyze-taskyusifeng/formax | Skill | 184 | 3mo ago | MIT | A | 55 | Codex |
| unbrokerKevRojo/Dulus | Skill | 508 | 3d ago | GPL-3.0 | A | 15 | Claude Code, Codex |
| obsidian-basesKevRojo/Dulus | Skill | 508 | 3d ago | GPL-3.0 | A | 63 | Claude Code, Codex |
| json-canvasKevRojo/Dulus | Skill | 508 | 3d ago | GPL-3.0 | A | 54 | Claude Code, Codex |
| obsidian-markdownKevRojo/Dulus | Skill | 508 | 3d ago | GPL-3.0 | A | 105 | Claude Code, Codex |
| obsidian-cliKevRojo/Dulus | Skill | 508 | 3d ago | GPL-3.0 | A | 102 | Claude Code, Codex |
| defuddleKevRojo/Dulus | Skill | 508 | 3d ago | GPL-3.0 | A | 74 | Claude Code, Codex |