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 tomzx/agents --skill create-needs-assessmentgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/create-needs-assessment)<a href="https://agentmods.dev/skills/tomzx/agents/create-needs-assessment"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-needs-assessment/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/tomzx/agents/create-needs-assessment"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-needs-assessment.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 | $0.00036 | $0.01452 |
| Opus 5.5 | $0.00014 | $0.00581 |
| Sonnet 5.5 | $0.00007 | $0.00290 |
| Haiku 4.5 | $0.00004 | $0.00145 |
Grade A, and why
create-needs-assessment 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 20d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess Needs
Evaluates whether a proposed feature addresses a genuine need before investing in feasibility or requirements. Acts as the earliest "should we build this?" gate in the SDLC pipeline by examining the problem, the stakeholders, the alternatives already available, and the cost of not building it.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - If no argument is provided, use
$ISSUE_TITLEand$ISSUE_BODYas the feature description (and$ISSUE_NUMBERto link the feature). - A reviewed, prioritized GitHub issue or feature description provided as
$1 - Read any files present under
.sdlc/context/(project-overview.md,goals.md,architecture.md,conventions.md) for project-level context - Apply any artifact style rules found in
conventions.mdto the produced document
When to Skip
Skip this phase, and record a one-line note naming the signal, when the issue is maintainer-authored and states the need and its acceptance criteria. The need is already established by the issue author, so the note is the record rather than a full assessment.
Steps
- Read the issue or feature description. Fetch from GitHub if a URL is provided.
- Read
.sdlc/context/project-overview.mdto understand project scope, goals, and constraints. - Identify the problem the feature claims to solve. If the issue only describes a solution (a feature), work backward to the underlying problem.
- Identify the stakeholders: who experiences this problem and who benefits from the solution.
- Assess the evidence: is the need demonstrated by user requests, support tickets, usage data, competitive analysis, or is it an assumption?
- Assess what happens if we do nothing: the cost of the status quo, including workarounds people already use.
- Assess alternative paths: could this need be met by an existing feature, a configuration change, better documentation, or a process change instead of new code?
- Read
.sdlc/context/goals.mdif present, then assess strategic alignment: which specific objective and key result does this need advance, or is it tangential? Ifgoals.mdis absent, note that alignment cannot be checked and flag it as an open question. - For each dimension, assign a rating: Strong / Moderate / Weak / None.
- Derive the overall needs verdict: Needed / Nice-to-have / Not needed.
- Derive the feature directory name
N-<slug>following the Feature Directory Naming convention inskills/sdlc/references/shared.md: use the issue number asNwhen one is available, otherwise ap-prefixed sequence number (p1,p2, ...) marking the feature as pending a placeholder issue. Record the related issue number in the frontmatterissuefield only when an issue exists. - Write the output to
.sdlc/features/N-<slug>/needs-assessment.md, creating the directory if it does not exist.
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.
- 20d ago Changed · +5 lines 6c954d314cb4
- 22d ago Changed · +12 lines 0dd4f589bdc9
- 27d ago Changed e6e213391eef
- 2mo ago First seen · 95 lines · 36 tokens per session scan A 7e54a053e475
create-needs-assessment is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,452 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
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…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…