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 skills/vepo/issues/review-code-structurenpx skills add vepo/issues --skill review-code-structuregit clone --depth 1 https://github.com/vepo/issuesWhat 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 | $0.00035 | $0.00527 |
| Opus 5 | $0.00017 | $0.00264 |
| Sonnet 5 | $0.00007 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
review-code-structure 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 2d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Java architect reviewing the Issues codebase. Produce a read-only structural audit — do not change code unless the user explicitly asks to fix findings afterward.
Prerequisites: Read ARCHITECTURE.md and docs/domain-specification.md before auditing.
Scope
Default: full repository (src/main/java/dev/vepo/issues/, src/main/webui/, tests).
If the user names a package or path, restrict scope but still check cross-package imports.
Output
Write one report:
reports/code-structure-review-{sequential}-{dd-MM-yyyy-HH-mm-ss}.md
Severity: critical | major | minor | suggestion.
Do not ask for confirmation before starting. Do not apply refactors in this command.
Phase 1 — Inventory
- List feature packages from ARCHITECTURE.md §5.
- Build type inventory: endpoints, repositories, services, entities, Request/Response records.
Phase 2 — Layer compliance
Read .cursor/rules/issues-layered-architecture.mdc.
| Check | Pass criteria |
|---|---|
| Endpoint → Repository bypass | Endpoints with multi-entity logic use *Service |
| Service → EntityManager | Services use repositories, not EM directly |
| Repository purity | No business rules or HTTP in repositories |
Phase 3 — HTTP contract
Read .cursor/rules/issues-http-contract.mdc.
- All
*Request/*Responseare records ArchitectureTestwould pass
Phase 4 — Bounded contexts
Read .cursor/rules/issues-bounded-contexts.mdc.
- Package dependency direction matches domain spec
- No unrelated cross-package repository access
Phase 5 — Duplication
- Repeated ticket/workflow validation logic
- Duplicate Angular HTTP calls
- Similar Response mapping patterns
Phase 6 — Frontend structure
- Services centralize API calls
- Components stay presentation-focused
Report template
# Code structure review — Issues
## Summary
(2–3 sentences)
## Findings
### Critical
- ...
### Major
- ...
### Minor / suggestions
- ...
## Recommended next steps
1. ...
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.
- 2d ago First seen · 93 lines · 35 tokens per session scan A 30e02af813cc
review-code-structure is a skill published in the GitHub repository vepo/issues (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 527 once invoked, about $0.0002 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
reference-signal-forms
Explains the mental model and architecture of the code under packages/forms/signals. You MUST use this skill any time you plan to work with code in packages/forms/signals.
reference-compiler-cli
Explains the mental model and architecture of the code under packages/compiler-cli. You MUST use this skill any time you plan to work with code in packages/compiler-cli.
angular-new-app
Creates a new Angular app using the Angular CLI. This skill should be used whenever a user wants to create a new Angular application and contains important guidelines for how to effectively create a modern Angular application.
dist-build-migration
Migrate an Nx package to build to a local dist/ directory with nodenext module resolution, exports map, and @nx/nx-source condition.
review-pending-pr-reviews
Review, grill, edit, and post pending PR review drafts saved by /review-pr (or its batch/cron runners). Lists drafts that have not yet been posted, walks the maintainer through each finding, then posts, closes, or discards. Use when the user says "post my pending reviews", "what reviews are waiting", "go through the…
nx-generate
Generate code using nx generators. INVOKE IMMEDIATELY when user mentions scaffolding, setup, structure, creating apps/libs, or setting up project structure. Trigger words - scaffold, setup, create a new app, create a new lib, project structure, generate, add a new project. ALWAYS use this BEFORE calling nxdocs or…