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/rocky2431/ultra-builder-proWrote 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/rocky2431/ultra-builder-pro/ultra-deliver)<a href="https://agentmods.dev/commands/rocky2431/ultra-builder-pro/ultra-deliver"><img src="https://agentmods.dev/badge/commands/rocky2431/ultra-builder-pro/ultra-deliver/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/rocky2431/ultra-builder-pro/ultra-deliver"><img src="https://agentmods.dev/badge/commands/rocky2431/ultra-builder-pro/ultra-deliver.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 | $0.00011 | $0.01722 |
| Opus 5 | $0.00005 | $0.00861 |
| Sonnet 5 | $0.00002 | $0.00344 |
| Haiku 4.5 | $0.00001 | $0.00172 |
Grade A, and why
ultra-deliver 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 11d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ultra-deliver
Workflow Tracking (MANDATORY)
On command start, create tasks for each major step using TaskCreate:
| Step | Subject | activeForm |
|---|---|---|
| 0.1 | Validate /ultra-test Passed | Validating test results... |
| 0.2 | Check Uncommitted Changes | Checking git status... |
| 1 | Documentation Update | Updating documentation... |
| 1.1 | Update CHANGELOG.md | Updating changelog... |
| 1.2 | Generate Technical Debt Report | Generating debt report... |
| 1.3 | Update README.md | Updating readme... |
| 2 | Production Build | Building for production... |
| 3 | Version & Release | Bumping version and tagging... |
| 4 | Persist Results | Persisting delivery report... |
Before each step: TaskUpdate → status: "in_progress"
After each step: TaskUpdate → status: "completed"
On context recovery: TaskList → resume from last incomplete step
Prepare release after /ultra-test passes: update documentation, build, bump version, tag, and push.
Pre-Delivery Validations (v7 — advisory + user decision)
v7 change: validations surface state and recommend; the user decides. Only irreversible operations (real git push, real publish, real release tag) hard-block.
Validation 1: /ultra-test Passed
Read .ultra/test-report.json and report:
- File exists? (if not: "Run /ultra-test first" — recommended, not blocking)
passedistrue? (if not: listblocking_issues)git_commitmatches current HEAD? (if not: "Code changed since last test")
If anything fails, use AskUserQuestion with <ask_user_format>:
- Re-ground: which validation(s) failed
- Recommend: re-run /ultra-test before delivering
- Options: A) Re-run /ultra-test now, B) Proceed anyway and accept risk (records gap), C) Cancel delivery
Validation 2: No Uncommitted Changes
Run git status and verify working directory is clean.
If unclean:
- Use
AskUserQuestionto confirm:- Option A: "Auto-commit all changes" → commit with
chore: pre-delivery cleanup - Option B: "Review changes first" → show
git diff --statand ask again - Option C: "Block delivery" → stop and let user handle manually
- Option A: "Auto-commit all changes" → commit with
- If user approves commit but it fails (conflicts, etc.) → block and report
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.
- 11d ago First seen · 197 lines · 11 tokens per session scan A d15bba71d7e3
ultra-deliver is a command published in the GitHub repository rocky2431/ultra-builder-pro (11 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,722 once invoked, about $0.0001 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 commands, from other repositories
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
ship
Deploy feature through automated staging validation to production with rollback testing.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
ship
Ship is the operational release-prep flow for a connected project repo.
release-plan
A release-planning command for a software change. It documents the release scope, rollback plan, gradual or full rollout, and monitoring before waiting for human approval.
create-pr
Push the current branch and open a pull request into main with a structured description derived from the branch's commits and the open issues it resolves.