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 joelbrilliant/agentic-delivery-skills --skill qa-to-engineering-briefgit clone --depth 1 https://github.com/joelbrilliant/agentic-delivery-skillsWrote 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/joelbrilliant/agentic-delivery-skills/qa-to-engineering-brief)<a href="https://agentmods.dev/skills/joelbrilliant/agentic-delivery-skills/qa-to-engineering-brief"><img src="https://agentmods.dev/badge/skills/joelbrilliant/agentic-delivery-skills/qa-to-engineering-brief/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/skills/joelbrilliant/agentic-delivery-skills/qa-to-engineering-brief"><img src="https://agentmods.dev/badge/skills/joelbrilliant/agentic-delivery-skills/qa-to-engineering-brief.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 | $0.00053 | $0.00517 |
| Opus 5.5 | $0.00021 | $0.00207 |
| Sonnet 5.5 | $0.00011 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
qa-to-engineering-brief 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA to Engineering Brief
Overview
Use this skill when a bug report is too vague for a builder but too real to ignore.
The output is not a diagnosis essay. It is a brief a builder can execute and a reviewer can verify.
When to Use
- User reports something broken.
- Screenshot shows confusing UI state.
- QA notes are scattered across chat.
- A bug seems intermittent.
- A failing workflow needs reproduction steps.
- You need to turn panic into an engineering slice.
Brief Structure
# [Short bug title]
## User-visible problem
[What the user experienced]
## Expected behaviour
[What should happen]
## Actual behaviour
[What happened]
## Evidence
[Screenshots, logs, run IDs, URLs, files, timestamps]
## Reproduction steps
1.
2.
3.
## Scope
In:
Out:
## Suspected area
[Files, services, components, data path]
## Severity
HIGH / MEDIUM / LOW with rationale
## Acceptance criteria
- [ ] Behaviour fixed
- [ ] Regression test added
- [ ] Runtime/browser/API proof captured
## Required verification
[Exact tests and smoke checks]
## Owner / role
[Builder or triage owner]
Severity Guide
HIGH:
- data loss;
- security or permission breach;
- payment/money/account impact;
- production feature structurally inert;
- user cannot complete core workflow.
MEDIUM:
- important workflow degraded;
- no regression test catches plausible failure;
- misleading user-facing state;
- recoverable but costly failure.
LOW:
- minor UX issue with no workflow break;
- copy/visual defect;
- small edge case with clear workaround.
Evidence Rules
- Screenshots need a timestamp or context.
- Logs need file/source and relevant lines.
- User quotes are evidence of perception, not root cause.
- Reproduction steps must be concrete enough for another agent.
- If you cannot reproduce, say what was tried and what remains unknown.
Anti-patterns
- "It feels broken" with no expected behaviour.
- Starting with suspected code before user impact.
- Filing a giant omnibus bug.
- Severity based on emotion instead of regression impact.
- Acceptance criteria that say "fix it".
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 · 105 lines · 53 tokens per session scan A 1e143569e4fa
qa-to-engineering-brief is a skill published in the GitHub repository joelbrilliant/agentic-delivery-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 517 once invoked, about $0.0002 per session on Opus 5.5. 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
doca-flow
DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Also covers pipe validation…
doca-debug
Use this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca symbol, a runtime call returning DOCAERROR, a silent service or tool, or a stack trace / valgrind / core dump — and needs the layered ladder (install → version → build → link → runtime →…
compute-sanitizer-diagnose-cuda-bugs
Detect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the report. Use when…
dynamo-interconnect-check
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
jetson-print-bsp-info
Use when you need to print Jetson BSP info (L4T version, board configs, rootfs state) from a LinuxforTegra root on the host PC. This is an example skill.