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 agentmods add skills/ndisisnd/cook/graphqlnpx skills add ndisisnd/cook --skill graphqlgit clone --depth 1 https://github.com/ndisisnd/cookWhat 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 | $0.00044 | $0.01809 |
| Opus 5 | $0.00022 | $0.00905 |
| Sonnet 5 | $0.00009 | $0.00362 |
| Haiku 4.5 | $0.00004 | $0.00181 |
Grade A, and why
graphql 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 2d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GraphQL Standards
Source: GraphQL Best Practices · Apollo Naming Conventions · GraphQL Schema Design
Priority: P0 — Schema Correctness
Nullability
The GraphQL spec makes every field nullable by default. A wrong ! is not just inaccurate — when a non-null field resolver returns null, GraphQL propagates the null upward through the response tree, wiping out the nearest nullable parent. One bad guarantee can null out an entire object from the client's response (graphql.org).
- Mark a field non-null (
!) only when the server can guarantee it will never be null — not just "usually non-null". - Mutation payload root fields (
user,order) must be nullable — the mutation may fail and return errors instead of data. - List elements and the list itself have separate nullability:
[User!]!means a non-null list of non-null users. ID!is always non-null — if you have an ID, it exists.
Scalars & Custom Types
- Use built-in scalars:
String,Int,Float,Boolean,ID. - Add custom scalars for domain types:
DateTime,Date,URL,EmailAddress,JSON. DON'TuseStringfor dates, emails, or URLs — custom scalars carry semantic meaning, enable server-side validation, and surface intent in generated client types.
See refs/schema-design.md for custom scalar declaration examples.
Mutation Shape
Every mutation must take a single input argument typed as an Input object and return a Payload type — never a naked entity, never Boolean (Apollo).
See refs/schema-design.md for input/payload design rationale and full examples.
Global Object Identification
Implement the Node interface (graphql.org) for any type that clients need to refetch individually. The id field must be globally unique across all types — base64-encode the type and database ID (base64("User:123")), never expose raw database IDs. Without this, Apollo Client and Relay cannot correctly normalise their caches.
What ships with it
7 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.
- 2d ago First seen · 139 lines · 44 tokens per session scan A f311efcfa68e
graphql is a skill published in the GitHub repository ndisisnd/cook (2 stars, last pushed 22d ago), licensed MIT. It adds 44 tokens to every session and 1,809 once invoked, about $0.0002 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
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by BitFun's unified Review mechanism instead.…
wechat-article-writer
公众号/自媒体全流程。根据用户表述自动匹配:撰写文章、封面图、正文插图、风格提取。支持多种写作风格。当用户提到写公众号、技术博客、公众号封面、正文插图、步骤图、演示图、流程示意、分析写作风格、克隆文风、模仿爆款、提取风格时使用。详见 reference 目录。.
miniapp-dev
Develops, maintains, and generates BitFun MiniApps (Zero-Dialect Runtime). Use when (1) working on miniapp framework code under src/crates/assembly/core/src/miniapp/ or src/web-ui/src/app/scenes/miniapps/; or (2) generating / creating / designing a NEW MiniApp for the user — including any request like "做一个小应用 / 生成…
vibe-research
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
investigate
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug…