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 keithhegit/ultra-orchestration --skill ultra-qagit clone --depth 1 https://github.com/keithhegit/ultra-orchestrationWrote 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/keithhegit/ultra-orchestration/ultra-qa)<a href="https://agentmods.dev/skills/keithhegit/ultra-orchestration/ultra-qa"><img src="https://agentmods.dev/badge/skills/keithhegit/ultra-orchestration/ultra-qa.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 5.1 | $0.00062 | $0.00253 |
| Opus 5 | $0.00031 | $0.00127 |
| Sonnet 5 | $0.00012 | $0.00051 |
| Haiku 4.5 | $0.00006 | $0.00025 |
Grade A, and why
ultra-qa 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 8d 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.
What it actually says
Ultra QA
QA validates behavior, not just code shape.
Two Modes
- static mode: inspect code, diffs, tests, and artifacts when execution is not possible
- dynamic mode: run commands or tests when the environment allows it
Do not pretend dynamic evidence exists when it does not.
Scenario Set
Cover at least:
- happy path
- error path
- regression risk
- user-visible behavior
- missing tests that should exist later
Failure Routing
- send failures to
Executewhen the plan remains valid - send failures to
Planwhen QA exposes a deeper requirement or architecture flaw
Output
Return:
- scenarios exercised
- static evidence
- dynamic evidence, if any
- pass or fail
- residual risks
- reroute recommendation when failed
Read qa-modes before running verification.
What ships with it
2 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.
- 8d ago First seen · 46 lines · 62 tokens per session scan A 93a4855ec6f6
ultra-qa is a skill published in the GitHub repository keithhegit/ultra-orchestration (6 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 253 once invoked, about $0.0003 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 skills, from other repositories
gsd-add-tests
Generate tests for a completed phase based on UAT criteria and implementation.
gsd-verify-work
Validate built features through conversational UAT.
gsd-audit-uat
Cross-phase audit of all outstanding UAT and verification items.
allium
Give your AI agents something more useful than a prompt. Velocity through clarity.
load-test-ops
Trigger, monitor, update, profile, and stop Camunda load tests using gh CLI and kubectl directly — no MCP server required.
specx-tests
Add or refine tests for specx Python services. Use when creating unit tests for use cases/services, integration tests for FastAPI controllers or infrastructure adapters, e2e smoke tests, architecture import guardrails, DI override tests, pytest fixtures, or coverage and boundary checks.