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 agentmods add commands/vepo/issues/review_feature_cataloggit clone --depth 1 https://github.com/vepo/issuesWrote 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/commands/vepo/issues/review_feature_catalog)<a href="https://agentmods.dev/commands/vepo/issues/review_feature_catalog"><img src="https://agentmods.dev/badge/commands/vepo/issues/review_feature_catalog.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 | $0.00026 | $0.00897 |
| Opus 5 | $0.00013 | $0.00449 |
| Sonnet 5 | $0.00005 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
Review Feature Catalog 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 6d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Product Owner for Issues running a full feature-catalog review. Act as .cursor/agents/product-owner.md. Produce a read-only product audit — do not change code or docs unless the user explicitly asks to apply fixes afterward.
Prerequisites: Read docs/feature-catalog.md, docs/domain-specification.md, and docs/backlog.md. Skim Angular routes under src/main/webui/ and relevant endpoints when verifying a row.
Scope
Default: every row in the feature catalog (UI table + API-only table) and Dev personas.
If the user names a Feature name, route prefix, or feature/<slug>.md, restrict to that subset but still note cross-feature navigation links (e.g. hub → Kanban).
Output
Write one report:
reports/feature-catalog-review-{sequential}-{dd-MM-yyyy-HH-mm-ss}.md
Severity: critical | major | minor | suggestion.
Do not ask for confirmation before starting. Do not edit src/**, catalog, or backlog in this command.
Phase 1 — Inventory
- List all catalog Feature rows (UI + API-only) with Route / API and Roles.
- Inventory Angular routes (router config) and primary shell menus.
- Note matching
feature/*.mdfiles where a capability has analysis.
Phase 2 — Route and role compliance
For each catalog row:
| Check | Pass criteria |
|---|---|
| Route exists | Path in router matches Route (params allowed) |
| Reachable | Menu or documented entry points match Steps |
| Roles | Guards / menu visibility / API roles align with Roles |
| Dev persona | At least one persona can exercise the happy path |
Mark missing implementation, extra undocumented route, or role mismatch.
Phase 3 — Happy-path steps
For each UI row, verify Steps against UI labels and flows:
- Step verbs and screen names exist (Portuguese labels as in catalog)
- Linked features (e.g. Burndown from Kanban) still exist
- Capability gates (
GET /auth/capabilities, LOCAL-only) match catalog notes - Broken or impossible steps → finding with evidence
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.
- 6d ago First seen · 108 lines · 26 tokens per session scan A 5b92cae5833f
Review Feature Catalog is a command published in the GitHub repository vepo/issues (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 897 once invoked, about $0.0001 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 commands, from other repositories
test-ui
Run a Playwright browser smoke test on the current app.
paul:verify
Guide manual user acceptance testing of recently built features.
plan-spec
仅在人工明确安排 UI 自动化时，根据任务、产品规则或原型生成独立行为 Spec.
journey-audit
Outside-in product audit as a deep session — 7 read-only roles check what the site promises against what the code does, what a user experiences, what arrives by mail, and what the data says is used. Writes a dossier; needs a per-repo journey-manifest.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.
verify-pr
Verify a PR's frontend changes through browser automation.