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 6529-Collections/6529seize-frontend --skill write-skillsgit clone --depth 1 https://github.com/6529-Collections/6529seize-frontendWrote 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/6529-collections/6529seize-frontend/write-skills)<a href="https://agentmods.dev/skills/6529-collections/6529seize-frontend/write-skills"><img src="https://agentmods.dev/badge/skills/6529-collections/6529seize-frontend/write-skills/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/6529-collections/6529seize-frontend/write-skills"><img src="https://agentmods.dev/badge/skills/6529-collections/6529seize-frontend/write-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Rogue Agent · line 6 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00063 | $0.01542 |
| Opus 5 | $0.00032 | $0.00771 |
| Sonnet 5 | $0.00013 | $0.00308 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
write-skills 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 10d 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.
Write Skills
Principles
- Keep each skill focused on one job. Split broad workflows into separate skills or references.
- Treat frontmatter as the routing surface. Put all "when to use this skill" guidance in
description, because the body is only loaded after the skill triggers. - Assume Codex is already capable. Add only procedural knowledge, repo-specific context, examples, scripts, and constraints that materially improve repeatability.
- Prefer clear instructions over scripts unless deterministic behavior, external tooling, or repeated code would reduce mistakes.
- Use progressive disclosure: keep
SKILL.mdlean, put large details in directly linkedreferences/, and keep output templates or reusable files inassets/. - Write imperative steps with explicit inputs, outputs, and validation.
- Test trigger behavior with prompts that should invoke the skill and prompts that should not.
Topics To Cover
When writing or reviewing a skill, decide whether each topic belongs in the skill:
- Frontmatter and trigger behavior
- Skill name and folder layout
- Task scope, anti-scope, and adjacent non-triggers
- Required inputs and expected outputs
- Step-by-step workflow
- Tool, command, or file conventions
- Scripts, references, and assets
- Validation and forward-testing
- Safety constraints, permissions, and destructive-action guardrails
- Maintenance notes, only when they change future use of the skill
If a topic is not needed for the skill's job, omit it. A short complete skill is better than a broad checklist pasted everywhere.
Workflow
-
Clarify the target job
Identify the narrow repeatable task, likely users, concrete prompts, expected outputs, and adjacent prompts that should not trigger the skill. If the job is ambiguous, ask for one or two examples before writing.
-
Choose name and location
Use lowercase letters, digits, and hyphens only. Keep the folder name identical to the skill name. In this repo, place repo-local skills under
ops/skills/<skill-name>/SKILL.mdunless the user asks for another skill location.
What ships with it
1 file 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.
- 10d ago First seen · 164 lines · 63 tokens per session scan A 407ca136178d
write-skills is a skill published in the GitHub repository 6529-Collections/6529seize-frontend (10 stars, last pushed today), licensed Apache-2.0. It adds 63 tokens to every session and 1,542 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…