IBM/CodeEngine contains tutorials and samples for IBM Cloud Code Engine, an environment for deploying workloads. Its tutorials teach complete deployment scenarios step by step, while its smaller samples show developers how to perform individual tasks or reuse them in their own Code Engine work. The catalogue skill helps coding agents work with these Code Engine examples.
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 IBM/CodeEngine --skill code-engine-specialistgit clone --depth 1 https://github.com/IBM/CodeEngineWrote 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/ibm/codeengine/code-engine-specialist)<a href="https://agentmods.dev/skills/ibm/codeengine/code-engine-specialist"><img src="https://agentmods.dev/badge/skills/ibm/codeengine/code-engine-specialist/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/ibm/codeengine/code-engine-specialist"><img src="https://agentmods.dev/badge/skills/ibm/codeengine/code-engine-specialist.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 Data Exfiltration · line 42 Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.Fix: Remove unnecessary filesystem scanning. If file access is needed, use explicit, scoped paths. Avoid reading ~/.ssh, ~/.aws, or credential directories.
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 | $0.00102 | $0.03231 |
| Opus 5.5 | $0.00041 | $0.01292 |
| Sonnet 5.5 | $0.00020 | $0.00646 |
| Haiku 4.5 | $0.00010 | $0.00323 |
Grade A, and why
code-engine-specialist 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 1mo 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY WORKFLOW - FOLLOW IN ORDER
Phase 0: Authentication Check (ALWAYS FIRST)
NEVER skip this step. Many Code Engine problems are authentication issues.
- Check authentication:
ibmcloud target - If not authenticated, ask user to configure IBM Cloud CLI and authenticate with:
ibmcloud login --sso(for SSO authentication)ibmcloud login --apikey <your-api-key>(for API key authentication)
- Verify success before proceeding
Success output:
🔐 Authentication Status Check
---
✅ Authenticated as: [email protected]
Account: Account Name (id...)
Region: us-south
Resource Group: Default
Ready to proceed!
Failure output:
❌ Not authenticated to IBM Cloud
Please authenticate using one of these methods:
• SSO: ibmcloud login --sso
• API Key: ibmcloud login --apikey <your-api-key>
After authentication, run your command again.
Phase 1: Source Code Analysis (ALWAYS SECOND)
Extract deployment context from local source code.
- List project files:
ls -laand find key files - Read and analyze key files:
- package.json → nodejs, npm, framework, port
- requirements.txt → python, pip, flask, django, fastapi
- Dockerfile → dockerfile, custom-build, container, port
- pom.xml → java, maven, spring-boot
- go.mod → golang, go
- .env.example → environment-variables, secrets
- config.yaml → environment variables, configmap
- config.json → environment variables, configmap
- Extract deployment keywords for documentation search
Output format:
📁 Analyzing Your Project
---
Found key files:
✓ package.json (Node.js application)
✓ Dockerfile (Custom container build)
Detected technologies:
• Runtime: Node.js 18.x
• Framework: Express.js
• Port: 3000
Deployment Keywords:
→ nodejs, express, dockerfile, environment-variables, port-configuration
Phase 2: Deployment Planning (ALWAYS THIRD)
Based on source code analysis, formulate deployment recommendations.
- Determine workload type (Application vs Job)
- Check for Dockerfile (create if missing using language-specific examples)
- Identify configuration needs (secrets, configmaps)
- Recommend resource allocation based on detected technologies
- Always put all secrets, clientIds, authentication credentials, etc. into a Code Engine secret
What ships with it
3 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.
- 1mo ago First seen · 361 lines · 102 tokens per session scan A 68dfcff0e43b
code-engine-specialist is a skill published in the GitHub repository IBM/CodeEngine (119 stars, last pushed 3d ago), licensed Apache-2.0. It adds 102 tokens to every session and 3,231 once invoked, about $0.0004 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
trigger-cost-savings
Analyze Trigger.dev tasks, schedules, and runs for cost optimization opportunities. Use when asked to reduce spend, optimize costs, audit usage, right-size machines, or review task efficiency. Combines static source analysis with live run analysis via the Trigger.dev MCP tools (listruns, getrundetails…
modal-serverless-gpu
Run approved CPU or GPU work through OpenScience computejob on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.
gcp-essentials
Use when running a small product on core Google Cloud via the gcloud CLI: a project, Cloud Run deploys, a locked-down Cloud Storage bucket, managed Cloud SQL, and least-privilege IAM wiring them together. NOT AWS (that is aws-essentials), NOT the CI pipeline that ships the image (that is deployment), NOT Postgres…
modal
Use when running Python or GPU workloads serverlessly on Modal — modal.App, inline container Images, gpu= on @app.function, Volumes for weight caching, Cron schedules, ASGI endpoints, modal run vs serve vs deploy. NOT managed prediction APIs with no container of your own (that is replicate); NOT SSH-able GPU boxes…
cloudflare
Use when working on Cloudflare's edge platform — wrangler.jsonc bindings, choosing between D1/KV/R2/Durable Objects/Queues, deploying a Worker or SPA via Static Assets, or designing around a Workers runtime limit. NOT generic CI/release (that is deployment), NOT Next.js framework wiring (that is nextjs), NOT DNS…
architecture-paradigm-serverless
Applies serverless FaaS patterns for event-driven workloads. Use when designing bursty workloads with minimal infrastructure and pay-per-execution cost model.