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 Ludovic33Fr/product-ai-toolbox --skill quality-review-ticketsgit clone --depth 1 https://github.com/Ludovic33Fr/product-ai-toolboxWrote 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/ludovic33fr/product-ai-toolbox/quality-review-tickets)<a href="https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/quality-review-tickets"><img src="https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/quality-review-tickets/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/ludovic33fr/product-ai-toolbox/quality-review-tickets"><img src="https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/quality-review-tickets.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 | $0.00064 | $0.01557 |
| Opus 5 | $0.00032 | $0.00779 |
| Sonnet 5 | $0.00013 | $0.00311 |
| Haiku 4.5 | $0.00006 | $0.00156 |
Grade A, and why
quality-review-tickets 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 12d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
quality-review-tickets
Fiche éditoriale
Objectif. Produire la pré-revue qualité d'un ou plusieurs tickets de backlog avant cérémonie de refinement.
Entrées. URL ou contenu du ticket, base documentaire produit, glossaire métier.
Sorties. Tableau des critères manquants par dimension, test INVEST argumenté, scénarios edge cases en Given/When/Then, dépendances détectées.
Cadence d'usage. Veille de chaque refinement, sur l'ensemble des tickets prévus.
Mode opératoire
Quand m'invoquer
L'utilisateur prépare un refinement et veut pré-réviser les tickets pour identifier les manques avant la cérémonie. Il me passe le contenu (texte, URL, ou liste de tickets) et la base documentaire à laquelle se référer si besoin.
Procédure
- Pour chaque ticket, examiner sa qualité sur cinq dimensions :
- User story présente et bien formée (En tant que / je veux / afin de).
- Critères d'acceptation explicites et testables.
- Scénarios au moins un nominal et idéalement un ou deux edge cases.
- Dépendances identifiées (tickets liés, services tiers, données requises).
- Cas hors-scope explicités.
- Tableau des manques : sur chaque dimension, marquer présent / partiel / absent et préciser ce qui manque.
- Test INVEST : pour chaque lettre, dire si elle est tenue (oui/non/partiel) et expliquer.
- Génération d'edge cases : 2-3 scénarios edge en Given/When/Then que le ticket ne couvre pas explicitement.
- Dépendances détectées : tickets potentiellement bloquants/bloqués, données nécessaires en amont, services tiers.
- Niveau de préparation : prêt pour refinement / besoin de clarification / à découper.
- Produire la sortie au format ci-dessous.
Format de sortie
# Pré-revue refinement — {date du refinement}
## Ticket {ID} — {titre}
### Tableau des manques par dimension
| Dimension | État | Manque |
|-----------|------|--------|
| User story | présent / partiel / absent | ... |
| Critères d'acceptation | ... | ... |
| Scénarios | ... | ... |
| Dépendances | ... | ... |
| Cas hors-scope | ... | ... |
### Test INVEST
- Independent : oui / non / partiel — {explication}
- Negotiable : ...
- Valuable : ...
- Estimable : ...
- Small : ...
- Testable : ...
### Edge cases manquants
Given {prérequis} When {action} Then {résultat}
Given {prérequis} When {action} Then {résultat}
### Dépendances détectées
- {ticket lié ou service tiers} — {nature de la dépendance}
- ...
### Niveau de préparation
**{prêt pour refinement | besoin de clarification | à découper}**
{1-2 phrases qui justifient.}
---
## Ticket {ID suivant} — {titre}
... (idem)
## Synthèse pour la cérémonie
- {n} tickets prêts
- {n} tickets nécessitant clarification : ID1, ID2
- {n} tickets à découper : ID3
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.
- 12d ago First seen · 174 lines · 64 tokens per session scan A 2b2cd93cd69b
quality-review-tickets is a skill published in the GitHub repository Ludovic33Fr/product-ai-toolbox (1 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 1,557 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
task-board-setup
Creates a Codex file-based task board. Explicit user invocation only.
tackle-issue
Start-of-work triage in this monorepo. Trigger on: a GitHub issue number ("tackle issue 99", "work on #42", bare #N), pasted proposal/spec text ("investigate this", "pressure-test this", "scope this"), or picker phrasing ("tackle the next issue", "what should I work on"). Read-only investigation that tries to falsify…
stale-proposals
Audit this repository's local proposal queue for stale entries: proposals still marked proposed, deferred, or accepted even though the work already shipped, plus old proposals whose subject has become inert. Reconcile proposals against plugin changelogs and first-parent Git history, automatically resolve only…
add-source
Interactively add a new source to feed-sources.md with type inference, https and name-uniqueness validation, and category checking against feed-categories.md. Appends a formatted row to the Active Sources table. Invoke with /feed-hermit:add-source.
quality-management-expert
Build comprehensive quality management solutions including QMS implementation, audit tracking, nonconformance management, and continuous improvement programs. Use when the user mentions a QMS, ISO 9001, audits and CAPA, nonconformance tracking, Six Sigma, or continuous improvement programs.
plan-to-tasks
Transform a plancreation planv{N}.md into a structured tasks.yaml + per-WP workpackages/.yaml using parallel Sonnet sub-agents. Use after plan-creation finishes when you need execution-friendly task structure.