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/joaoequer/oficina/reviewgit clone --depth 1 https://github.com/JoaoEquer/OficinaWrote 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/joaoequer/oficina/review)<a href="https://agentmods.dev/commands/joaoequer/oficina/review"><img src="https://agentmods.dev/badge/commands/joaoequer/oficina/review.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 | $0.00026 | $0.00451 |
| Opus 5 | $0.00013 | $0.00226 |
| Sonnet 5 | $0.00005 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
review 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 3d 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.
What it actually says
Review $ARGUMENTS (a PR number if given, otherwise the current working diff — staged and unstaged) against the Oficina house checklist. This command only reports; it never edits files. If fixes are wanted, that's a separate, explicit ask.
Read the diff, then check it against each item below. Don't restate the rule generically — point at the specific file:line that violates or satisfies it.
Blockers (security-baseline) — any failure here means the review fails outright:
-
workspaceId/userId/tenant identity comes from the authenticated context, never from the request body - Every new repository method filters by
workspaceId - Every new route has a permission guard/decorator, unless explicitly public
- No secret, token or credential committed;
.env.exampleupdated if new env vars were introduced - Input validated via DTOs (
class-validator); no rawreq.bodyaccess - Dates handled in UTC
Quality (engineering-philosophy):
- No speculative abstraction (generic repository, hexagonal ports/adapters, config built for a single use case)
- Complexity matches what the problem actually demands — no new dependency or service for something Postgres/the existing monolith already solves
- Tests cover a failure case, not only the happy path, for new logic
Process (git-workflow):
- Branch and commit messages follow convention (
feat:/fix:/chore:/etc., imperative mood) - The PR is one domain/topic — flag it if it mixes schema changes, an unrelated refactor and a new feature
- Migrations have descriptive names and were reviewed before merge
Report format: pass/fail per item with file:line evidence for failures, then a single verdict at the end — ship it / needs changes / blocked. Never close with a vague "looks good".
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.
- 3d ago First seen · 29 lines · 26 tokens per session scan A 289c2a3b43e3
review is a command published in the GitHub repository JoaoEquer/Oficina (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 451 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
product-spec-builder
Gather requirements and generate/update Product-Spec.md through structured interview.
domain-mapper
Research and map a domain/industry/technology into a structured Markdown database.
change-manager
Brownfield change workflow — propose, apply, verify, archive (OpenSpec-aligned).
code-review
Run parallel specialized review agents and produce aggregated quality report.
design-brief-builder
Generate Design-Brief.md through structured design interview.
reqforge-greenkeeper
Diagnose and fix ReqForge repository release gate failures.