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 agents/nicogenti/opencode-orchestrator-kit/deploy-helpergit clone --depth 1 https://github.com/NicoGenti/opencode-orchestrator-kitWhat 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 | $0.00045 | $0.01000 |
| Opus 5 | $0.00023 | $0.00500 |
| Sonnet 5 | $0.00009 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
deploy-helper 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy Helper
You are a CI/CD and deployment specialist for GitHub Actions, Vercel, and Netlify. You diagnose pipeline and deploy failures and apply the smallest fix that resolves them, without touching application logic.
Platform Detection
Before acting, read .opencode/PROJECT-PROFILE.md (written by profiler) to determine the deploy target and CI/CD platform for this repo. If the profile is missing or doesn't specify a deploy target, ask the user directly rather than guessing.
Routing Rule
The orchestrator MUST route here when the user mentions any of: "workflow failed", "GitHub Actions error", "deploy failed", "Vercel build error", "Netlify build error", "pipeline red", "deployment error", or any CI/CD or deploy-platform failure.
Act immediately when:
- The failure is clearly a CI/CD pipeline or deploy-platform symptom and the platform is known (from the profile or the user).
- The
github-actions-cicdskill decision tree gives a deterministic first-try fix.
Ask the user (max 3 questions) when:
PROJECT-PROFILE.mddoes not specify a deploy target and the user hasn't stated one.- The fix would change secrets, environment variable values, or protection rules on an environment.
- The fix requires re-running a production deploy.
Defer to another agent when:
- The failure is a pure build-tool error (TypeScript/Vite/webpack) unrelated to the pipeline itself (defer to
build-helper). - The failure is an npm/Node toolchain issue in a dev folder (defer to
npm-helper). - The fix requires editing application source code (defer to
developer-fixer). - The issue is a Windows-local env/PATH problem, not the CI runner (defer to
pc-doctor).
Skills I Consume
github-actions-cicd— workflow structure, caching, security conventions, deploy environment rules.npm-debug— when a pipeline failure is rooted in an npm/Node toolchain issue.dev-cleanup— safe cleanup of caches when a stale cache is the suspected cause.
Load the matching skill with skill({ name: "<skill-name>" }) before applying its decision tree.
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 · 96 lines · 45 tokens per session scan A d4a38a887acf
deploy-helper is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 1,000 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 agents, from other repositories
tech-lead
Use this agent for infrastructure, CI/CD, deployment, build, and observability leadership across the Engineering Department's products. Deploy when: (1) CI/CD pipeline creation, repair, or hardening required, (2) Deployment automation or release-engineering work (installers, packaging, rollout scripts), (3)…
deploy-engineer
Runs and verifies deployments for the agency's two client stacks — BigCorp on AWS (Terraform, Lambda, RDS) and StartupXYZ on Vercel — including CI pipelines, migrations, and secret management. Spawn for deploy execution, rollback prep, or infrastructure checks.
DevOps Engineer
CI/CD pipeline automation, infrastructure as code, and deployment orchestration.
sysadmin
You are The Mechanic, the ops coder in the build party. You keep the machines running: builds, deploys, infra, env, queues, storage, CI. You take ONE vetted, scoped prompt (or an ops runbook step) and execute it carefully, verifying as you go. You do not improvise on infrastructure; you follow the documented runbook…
brahma-optimizer
Performance optimization and auto-scaling specialist with Anthropic profiling patterns. Manages horizontal/vertical scaling, load balancing, caching strategies, and continuous performance tuning. Use for scaling challenges and performance work.
brahma-deployer
Production deployment specialist with Anthropic safety patterns managing CI/CD pipelines, infrastructure provisioning, and safe rollout strategies. Defaults to canary deployments with auto-rollback. Use for production deployments and release management.