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/codemie-ai/codemie-code/codemie-sdknpx skills add codemie-ai/codemie-code --skill codemie-sdkgit clone --depth 1 https://github.com/codemie-ai/codemie-codeWhat 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 | $0.00205 | $0.02721 |
| Opus 5 | $0.00102 | $0.01360 |
| Sonnet 5 | $0.00041 | $0.00544 |
| Haiku 4.5 | $0.00020 | $0.00272 |
Grade A, and why
codemie-sdk 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeMie SDK Asset Management
Manage CodeMie platform assets from the CLI.
Analytics requests (usage data, summaries, spending, activity, etc.) are handled by the codemie-analytics skill — use that instead.
Asset Types: assistants, workflows, datasources, integrations, skills, users, assistant-categories
Operations: list, get, create, update, delete
🚨 Project Clarification (MANDATORY)
Before proceeding with any work, you must determine which project to use by following these steps:
Step 1 — Fetch the User Profile
codemie sdk users me --json
This command returns user_id, username, email, is_admin, applications, and applications_admin.
Step 2 — Identify Available Projects
- If
is_admin = true: the user can access all projects on the platform, not just those listed inapplications. - If
is_admin = false: the user can only work with projects listed inapplications. - The default project is the one matching the user's email (e.g., for
[email protected], the default project is[email protected]).
Step 3 — Confirm the Project Selection
- If the user explicitly states a project name, or uses phrases like "use my project" or "in my project", proceed with the identified project (use the default project for phrases like "my project" or "my default project").
- In all other cases, ALWAYS ask the user which project to use.
Aks the user what project to use with the options as follows:
- Default project —
<user-email>(personal default project) - Choose a different project — let the user to manually type the project name.
Example prompt:
Which project should I use?
1. [email protected] (your default project)
2. Choose a different project
Note:
Only select a project automatically if the user has explicitly named it, or used clear phrases indicating the default (e.g., "my project", "my default project"). In all other situations, always ask for project clarification.
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 · 241 lines · 205 tokens per session scan A 22d667ac2ed4
codemie-sdk is a skill published in the GitHub repository codemie-ai/codemie-code (276 stars, last pushed 3d ago), licensed Apache-2.0. It adds 205 tokens to every session and 2,721 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
paperclip
Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.
omni-mcp
Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.
add-resend
Add Resend (email) channel integration via Chat SDK.
codegen
Code generation utilities for json-render. Use when generating code from UI specs, building custom code exporters, traversing specs, or serializing props for @json-render/codegen.
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
optimize-agentic-workflow
Analyze and reduce token consumption in agentic workflows — guardrail-specific entry points, measurement, and optimization techniques.