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 Joaonic/agentkit --skill qa-issue-specgit clone --depth 1 https://github.com/Joaonic/agentkitWrote 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/joaonic/agentkit/qa-issue-spec)<a href="https://agentmods.dev/skills/joaonic/agentkit/qa-issue-spec"><img src="https://agentmods.dev/badge/skills/joaonic/agentkit/qa-issue-spec/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/joaonic/agentkit/qa-issue-spec"><img src="https://agentmods.dev/badge/skills/joaonic/agentkit/qa-issue-spec.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 | $0.00067 | $0.02804 |
| Opus 5.5 | $0.00027 | $0.01122 |
| Sonnet 5.5 | $0.00013 | $0.00561 |
| Haiku 4.5 | $0.00007 | $0.00280 |
Grade A, and why
qa-issue-spec 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Issue Spec
Produce a complete, execution-ready QA package for a single issue.
Treat the issue as the source of truth, then enrich it with repository evidence and linked context. Read the issue title, body, comments, linked files, related code, existing tests, flags, migrations, schemas, and nearby modules before drafting the output.
Do not stop at a short checklist. Deliver a full package that a QA engineer, developer, or product manager can use immediately.
Operating principles
- Distinguish clearly between:
- explicit facts from the issue or codebase
- inferred behavior based on context
- unknowns that need confirmation
- Do not invent product rules silently. When a rule is missing, state the assumption.
- Prefer risk-based coverage over exhaustive noise.
- Favor concrete system behavior over generic QA advice.
- Reuse repository terminology exactly as found in the issue and codebase.
- When existing tests already cover part of the behavior, call that out and avoid duplicating them blindly.
Workflow
Follow this sequence.
1. Understand the issue
Fetch completo obrigatório — comandos (GitLab default):
# 1. Body completo + metadata (labels, milestone, assignees, state, dates, web_url)
glab issue view <N> --output json
# 2. Todos os comentários/notas (decisões, feedback, mudanças de scope)
glab issue view <N> --comments
# 3. MRs já vinculados à issue (contexto de implementação existente)
glab api "projects/:id/issues/<N>/related_merge_requests" 2>/dev/null || true
# 4. Issues relacionadas (parent, blocker, linked — entender fronteiras)
glab api "projects/:id/issues/<N>/links" 2>/dev/null || true
Exceção web/your-github-project (GitHub):
gh issue view <N> --json number,title,body,state,labels,milestone,assignees,url,comments
gh api "repos/{owner}/{repo}/issues/<N>/timeline" --jq '.[] | select(.event=="cross-referenced")' 2>/dev/null || true
Campos obrigatórios a consumir:
| Campo | Uso no QA package |
|---|---|
description (body) |
Requisitos, AC, user stories, contexto |
notes / comments |
Decisões de scope, feedback, esclarecimentos |
labels |
Prioridade (determina p0/p1/p2), tipo (bug vs feature), área |
milestone |
Ciclo de entrega, timeline |
assignees |
Contacto para open questions |
related MRs |
Implementação já feita (ajustar QA ao que existe) |
linked issues |
Parent/blocker — entender scope e fronteiras |
source_plan |
Se presente no body, ler plano para contexto completo |
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.
- 1mo ago First seen · 370 lines · 67 tokens per session scan A 9f7324a55c4c
qa-issue-spec is a skill published in the GitHub repository Joaonic/agentkit (2 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 2,804 once invoked, about $0.0003 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.