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 TanStack/intent --skill generate-skillgit clone --depth 1 https://github.com/TanStack/intentWrote 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/tanstack/intent/generate-skill)<a href="https://agentmods.dev/skills/tanstack/intent/generate-skill"><img src="https://agentmods.dev/badge/skills/tanstack/intent/generate-skill/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/tanstack/intent/generate-skill"><img src="https://agentmods.dev/badge/skills/tanstack/intent/generate-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 45 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00072 | $0.02405 |
| Opus 5.5 | $0.00029 | $0.00962 |
| Sonnet 5.5 | $0.00014 | $0.00481 |
| Haiku 4.5 | $0.00007 | $0.00241 |
Grade A, and why
generate-skill 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 21d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Author and maintain library skills
Work in the maintainer's library repository with their existing coding agent. Produce a source-grounded skill batch or focused update with task checks, a cumulative planning record, and a compact review. Intent supplies the procedure and deterministic evidence; your agent performs the authoring work.
1. Recover the task and choose the workflow
Use the current conversation, supplied diff, identified code/docs change, review report, or selected skill tree entry. Reuse the task, decisions, and evidence already established in this session; do not ask the maintainer to paste them again. Identify what developers need help doing and which package owns that task. If there is no usable task or review input, ask one question: “What do developers need help doing with this library?” Wait for the answer.
Check repository instructions and Git status before edits; preserve unrelated changes. Read maintainer commands when setting up the repository, adding a skill, or preparing a batch for review. When installing or updating CI, read workflow security before changing pins, triggers, or permissions. Use those commands for registration, metadata synchronization, and completion checks. Discover the package name, version, repository, skill root, and vocabulary from the repository. Use an established custom root; otherwise use skills/ inside the owning package, including in monorepos.
Before choosing or changing repository exports, follow repository distribution. For an export-only change, complete that procedure against existing skill records; use the authoring steps below only if guidance must change.
For an initial skill set or a request spanning several developer tasks, read initial batches. Reuse scope already approved in the conversation. For one concrete task, proceed directly below. During ordinary library work, keep the code change as the primary task. Read source review to identify affected guidance from actual changes and record completed reviews before handing off any of these workflows.
What ships with it
9 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.
- references/distribution.md 7.9 KB
- references/initial-batches.md 2.8 KB
- references/maintainer-commands.md 5.3 KB
- references/planning-records.md 9.5 KB
- references/review-signals.md 6.4 KB
- references/skill-format.md 7.5 KB
- references/source-review.md 6.5 KB
- references/task-quality.md 5.3 KB
- references/workflow-security.md 2.7 KB
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.
- 21d ago Changed 9b8a93b66738
- 1mo ago Changed f486c87024aa
- 1mo ago Changed · -369 lines · -8 tokens per session 99552b660536
- 1mo ago Changed · -7 lines c9631483abec
- 1mo ago First seen · 462 lines · 80 tokens per session scan A f18ba66eabb2
generate-skill is a skill published in the GitHub repository TanStack/intent (355 stars, last pushed 7d ago), licensed MIT. It adds 72 tokens to every session and 2,405 once invoked, about $0.0003 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.
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…