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.
git clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitWrote 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/commands/build-with-dhiraj/ai-workflow-framework-portability-kit/_conventions)<a href="https://agentmods.dev/commands/build-with-dhiraj/ai-workflow-framework-portability-kit/_conventions"><img src="https://agentmods.dev/badge/commands/build-with-dhiraj/ai-workflow-framework-portability-kit/_conventions/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/commands/build-with-dhiraj/ai-workflow-framework-portability-kit/_conventions"><img src="https://agentmods.dev/badge/commands/build-with-dhiraj/ai-workflow-framework-portability-kit/_conventions.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00671 |
| Opus 5.5 | $0.00000 | $0.00268 |
| Sonnet 5.5 | $0.00000 | $0.00134 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
_conventions 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command Conventions
Every slash command in this plugin follows a consistent structure so that the AI agent produces reliable, verifiable results. When authoring or updating a command file, include all of the sections below.
Required Sections
1. Preflight
Check prerequisites before doing any work:
- Project linked? — Verify
.vercel/project.jsonexists. If not, guide the user throughvercel link. - CLI available? — Confirm
vercelCLI is on PATH. - Repo state — Note uncommitted changes, dirty working tree, or detached HEAD when relevant.
- Scope — Detect monorepo (e.g.,
turbo.jsonorpnpm-workspace.yaml) and confirm which package is targeted.
Preflight failures should produce clear, actionable guidance — never silently skip.
2. Plan
Before executing, state what will happen:
- List the commands or MCP calls that will run.
- Flag destructive or production-impacting operations and require explicit user confirmation.
- If multiple strategies exist (MCP-first vs CLI-fallback), state which path was chosen and why.
3. Commands
The operational core. Follow these conventions:
- MCP-first, CLI-fallback — Prefer the Vercel MCP server for reads; use CLI for writes or when MCP lacks coverage.
- Structured output — Request
--format=jsonwhere available; parse and present results in a readable summary. - No secrets in output — Never echo environment variable values. Show names and metadata only.
- Confirmation for destructive ops — Production deploys, env removal, cache purge, and domain changes require an explicit "yes" from the user.
4. Verification
After execution, confirm the outcome:
- Re-read state (e.g.,
vercel ls,vercel env ls) to confirm the operation took effect. - Compare before/after where possible (e.g., deployment count, env var count).
- Surface errors or warnings from command output.
5. Summary
Present a concise result block:
## Result
- **Action**: what was done
- **Status**: success | partial | failed
- **Details**: key output (URL, counts, config changes)
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 · 80 lines · 0 tokens per session scan A cb10f630e3d6
_conventions is a command published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 671 tokens. 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 2026-09-21.
Other commands, from other repositories
deploy-verify
Run the server-side verification of a deployment and report pass or fail per check. Use when a deploy finished, after a cutover, or before closing a release.
tls-renew
Renew a Let's Encrypt certificate before it expires.
opsx-propose
Propose a new change - create it and generate all artifacts in one step.
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Archive
Archive a completed change in the experimental workflow.
opsx-explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.