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/srnichols/plan-forge/staging-deploynpx skills add srnichols/plan-forge --skill staging-deploygit clone --depth 1 https://github.com/srnichols/plan-forgeWrote 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/srnichols/plan-forge/staging-deploy)<a href="https://agentmods.dev/skills/srnichols/plan-forge/staging-deploy"><img src="https://agentmods.dev/badge/skills/srnichols/plan-forge/staging-deploy.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00030 | $0.00858 |
| Opus 5 | $0.00015 | $0.00429 |
| Sonnet 5 | $0.00006 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
staging-deploy scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -f https://staging-api.contoso.com/health How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Staging Deploy Skill
Trigger
"Deploy to staging" / "Push to staging environment"
Steps
0. Pre-flight Forge Validation
Use the forge_validate MCP tool to verify setup integrity before deploying.
1. Pre-Flight Checks
dotnet build --configuration Release
dotnet test --configuration Release --no-build
Conditional: Pre-Flight Failure
If Step 1 (Pre-Flight Checks) fails → STOP. Do not proceed to build.
2. Build Container
docker build -t contoso-api:staging -f Dockerfile .
docker tag contoso-api:staging registry.contoso.com/api:staging
docker push registry.contoso.com/api:staging
3. Run Migrations
# Apply pending database migrations
psql -h staging-db -d contoso_staging -f Database/migrations/latest.sql
4. Deploy
# Kubernetes
kubectl apply -f k8s/staging/ --context staging
# Or Docker Compose
docker compose -f docker-compose.staging.yml up -d
5. Verify
# Health check
curl -f https://staging-api.contoso.com/health
# Version check
curl https://staging-api.contoso.com/api/version
# Smoke test
dotnet test --filter "Category=Smoke" -- TestEnvironment=Staging
Safety Rules
- ALWAYS run tests before deploying
- ALWAYS verify health endpoint after deploy
- NEVER deploy to production using this skill
- Rollback:
kubectl rollout undo deployment/api --context staging
Temper Guards
| Shortcut | Why It Breaks |
|---|---|
| "It works locally, skip staging" | Local environments mask configuration, networking, and scaling issues that only surface in staging. |
| "Health check isn't needed yet" | Without health checks, orchestrators can't detect failures. A "successful" deploy may serve errors silently. |
| "I'll add monitoring after launch" | Post-launch is too late. Staging is where you verify observability works before production traffic arrives. |
| "One big deploy is simpler" | Monolithic deploys are harder to roll back. Deploy incrementally so failures are isolated to a single change. |
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 · 97 lines · 30 tokens per session scan A 5d7a1e1699b6
staging-deploy is a skill published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 858 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ring:creating-helm-charts
Creating Helm charts to Lerian conventions via ring:helm: standardized chart structure, full env-var coverage from .env.example, security defaults (runAsNonRoot, readOnlyRootFilesystem), ClusterIP-only services, and health probes; validates helm lint and template render. Use when creating, modifying, or reviewing a…
data-architect
Use this agent for database schema design, data modeling, query optimization, normalization decisions, and database architecture.
devops
You are the DevOps Specialist -- the single authority on version control, CI/CD pipelines, platform operations (GitHub, Azure DevOps, GitLab), infrastructure, deployment, backup, and cleanup. If it touches git, pipelines, or production infrastructure, it's yours.
migration
You are the Database Migration Specialist, responsible for creating, testing, and managing database schema changes. You ensure migrations are safe, reversible, and tested.
web-security-check
Use this agent to validate the live deployed surface of a web application before production promotion.
production-orchestrator
Use this agent for end-to-end PRD-to-production pipeline execution with zero-tolerance validation, compliance gates, and rollback capability.