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 Netcracker/qubership-ai-packages --skill problem-report-authoringgit clone --depth 1 https://github.com/Netcracker/qubership-ai-packagesWrote 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/netcracker/qubership-ai-packages/problem-report-authoring)<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/problem-report-authoring"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/problem-report-authoring/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/netcracker/qubership-ai-packages/problem-report-authoring"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/problem-report-authoring.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 | $0.00223 | $0.12189 |
| Opus 5.5 | $0.00089 | $0.04876 |
| Sonnet 5.5 | $0.00045 | $0.02438 |
| Haiku 4.5 | $0.00022 | $0.01219 |
Grade A, and why
problem-report-authoring 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 22d 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 — 628 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring a problem report
This skill governs what a problem report establishes before it is written, what each part of it
carries, and how a reviewer detects a bad one without the author present. Wording, tense, sentence
length, and dialect belong to the developer-style skill of the language the report is written in
(english-developer-style for English); load it too.
The artifacts under it share one structure: a bug report, a feature or change request, a question
where you are not sure the behavior is a defect, a support ticket to a vendor, and a short problem
message to a colleague. The channel can be any tracker, a forum, a support portal, or a mailing list,
and the project can be someone else's or your own: the person who picks the report up months from now
knows no more than a stranger would. What differs between them is length, what may be left unsaid,
which rules lapse, and the slots each genre adds: the opening and the slots of a request are in
references/request-genre.md, the question and the support ticket in
references/question-and-support-ticket.md, the colleague message in references/colleague-message.md,
and what a team's own backlog reduces in references/project-conventions.md. The head of §11 says
which checks each genre owes.
The form you already know is the wrong one. A change description is written for a reader who holds the diff: it names the symptom and moves at once to the mechanism and the fix, inside a project both of you work on. A triager holds no diff, your cause is a guess, and the fix is the project's to choose, so that shape produces a report that opens inside the target project's internals and argues for a patch. Writing a report in the shape of a pull request description is the failure this skill exists to prevent.
1. The readers
Every rule below names the reader it exists for. A sentence that answers none of their questions belongs somewhere else.
| Reader | Holds | Asks |
|---|---|---|
| R1 Triager | Your text, the project's templates and support policy, about a minute | Is this a defect in our project? Does it reproduce? On a version we support? Is it a duplicate? |
| R2 Maintainer | The whole report, plus the project's design constraints | Which behavior is correct here? Whom does this affect? What breaks if we change it? For a request: who is blocked, what does it cost, how will we know it worked? |
| R3 Whoever picks it up | The report and a fresh checkout, months later | How do I reproduce this? Is the expectation precise enough to write a test against? |
| R4 A searcher | The same error string, or their own use case | Is this my problem? On which versions? What do I do until it is fixed? |
| R5 A colleague | Three lines of chat, mid-task | Is this mine? What do you need from me? What did you already rule out? |
What ships with it
6 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.
- 22d ago Changed · +65 lines 982ec1c21708
- 25d ago First seen · 563 lines · 223 tokens per session scan A e806afed0b1f
problem-report-authoring is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed today), licensed Apache-2.0. It adds 223 tokens to every session and 12,189 once invoked, about $0.0009 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 2026-09-23.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
remove
Remove a deployed framework or addon from the current workspace.