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/codoop/codoop-flow/codoop-initnpx skills add Codoop/codoop-flow --skill codoop-initgit clone --depth 1 https://github.com/Codoop/codoop-flowWhat 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 | $0.00067 | $0.01200 |
| Opus 5 | $0.00034 | $0.00600 |
| Sonnet 5 | $0.00013 | $0.00240 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
codoop-init 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 yesterday.
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codoop Init
Initialize codoop-flow from the repository that exists or the empty project the
user explicitly asks to create. Use only these system project types: backend,
web, desktop, and mobile.
Locate the absolute directory containing this SKILL.md as $SKILL before
running the plugin-level Runtime commands below. Every host that installs the
whole plugin (Codex, Claude Code, Cursor, ...) keeps the Runtime at
$SKILL/../../runtime/codoop-flow/.
Output Language
Preserve an existing explicit output_language unless the user asks to change
it. When it is missing or a new config is being created, ask which output
language to use before running setup. Ask one plain-language question, recommend
the current conversation language, mention "auto", and accept any BCP 47
language tag. Common choices include "zh-CN", "zh-TW", "en", "ja",
"ko", "es", "fr", "de", "pt-BR", "it", "ru", "ar", "hi",
"id", "tr", "vi", and "th"; do not present this as a closed list.
Pass the answer as --output-language <language>.
Use the configured language for user-facing prose. "auto" follows the user's
current language. An explicit request for the current task overrides the config.
User Role
Preserve an existing explicit user_role unless the user asks to change it.
For a new config or a config without this setting, ask after resolving output
language, one plain-language question at a time. Offer: developer (研发 / 工程师),
product_manager (产品经理), designer (设计师), operations (运营 / 市场 / 销售),
founder (管理者 / 创业者), and general (普通用户 / 其他行业). Pass the answer as
--user-role <role>.
user_role changes only the live conversation: use normal professional language
within that role's field, and explain cross-field topics in plain language. It
does not measure ability. An explicit request such as “说简单点” or “讲专业一点”
overrides it for the current conversation. Never apply it to code, PRD, Spec,
Plan, Todo, reports, agent prompts, or other generated files; those stay precise
and professional.
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.
- yesterday First seen · 107 lines · 67 tokens per session scan A 3b380d1062c9
codoop-init is a skill published in the GitHub repository Codoop/codoop-flow (5 stars, last pushed 8d ago), licensed MIT. It adds 67 tokens to every session and 1,200 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
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
ss-studio
Turn a product brief and optional references into three distinct creative directions, a human-selected StyleSeed interaction plan, generated image/video asset jobs, a working UI prototype, and a verified prototype-first showcase reel. Use for client concepts, app interaction exploration, trendy but coherent UI…
apple-app-store-reviewer
Audit Apple-platform apps before App Store submission or resubmission. Use for iOS, iPadOS, macOS, tvOS, watchOS, and visionOS release reviews involving source code, archives or IPAs, App Store Connect metadata, screenshots, subscriptions, login, privacy manifests, AI features, UGC, age ratings, review notes, or an…
agent-safety
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or…
compose-multiplatform
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…
notes-keeper
Read, search, and write notes in the opendray file-system vault. Use this whenever the user mentions "notes", "daily log", "project doc", "TODO list", or wants to persist context that should survive across sessions.