Borrowing it
Nothing to install: this file belongs to Hackbyrd/orbital-express. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Hackbyrd/orbital-express/main/.claude/skills/review-conventions/SKILL.mdgit clone --depth 1 https://github.com/Hackbyrd/orbital-expressWrote 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/hackbyrd/orbital-express/review-conventions)<a href="https://agentmods.dev/skills/hackbyrd/orbital-express/review-conventions"><img src="https://agentmods.dev/badge/skills/hackbyrd/orbital-express/review-conventions/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/hackbyrd/orbital-express/review-conventions"><img src="https://agentmods.dev/badge/skills/hackbyrd/orbital-express/review-conventions.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 | $0.00065 | $0.01274 |
| Opus 5.5 | $0.00026 | $0.00510 |
| Sonnet 5.5 | $0.00013 | $0.00255 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
review-conventions 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 2mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review against conventions (self-audit)
Run this against the files you created/changed BEFORE saying a task is done, or when reviewing a diff. Go through every applicable item; for each, point to the file:line and fix violations. The authoritative rules are docs/conventions.txt and the README — this is the fast checklist.
First run dependency-free yarn conventions:check. This self-audit remains mandatory even when the automated check passes.
Feature structure
- Plan/sign-off happened before scaffolding or edits.
- Every
app/<Feature>has complete standard structure; no model-only/table-only exceptions. Extra domain files are allowed. -
yarn repair <Feature> --dry-runwas reviewed before repair; repair did not overwrite existing files; reported wiring ambiguity was resolved manually. - Root routes/models/workers/errors rely on auto-discovery; actions live in
actions/.
Every JS file
- Header comment →
'use strict'→ env → built-ins → third-party → services → helpers → models → queues (queue.get('XQueue')instances, right after models) → consts →module.exports(before methods) → methods. - Imports ordered by increasing length; plain requires before destructured.
- Every named function closed with
// END <name>. - No
requireof a feature's ownservices/socketfrom an action it's called by (use the context object).
Actions / controllers / routes
- Action name
V{version}{Action}[By{Role}][On{Device}]; file matches. - JSDoc lists route, auth,
Roles,req.args,Success, and everyError:code. - Uses
req.args(neverreq.body/req.query); POST/GET only;req.args = valueafter Joi (type coercion). - Joi-validates args; HTTP action returns
errorResponse(req, ...)(orerrorResponseRollback(t, ...)inside a transaction); socket/task throws;catchre-throws (no manual 500). - Returned records exclude sensitive fields (
attributes: { exclude: models.x.getSensitiveData() }). - Action AND controller have JSDoc headers (route, auth,
Roles, args, Success, every Error). - Flat success
{ status, success: true, ...payload }; status 200/201/202 correct; nodatanesting. - Controller is thin (role → action →
res.status(result.status).json(result),next(error)); route is registered in the feature (root discovery is automatic). - Role/device variants are separate methods (no role
if/elsein one); pure logic extracted tohelper.js. - Generated via
yarn gen(not hand-created); existing source/test/mailer targets were not overwritten; action/task indexes are deduplicated and deterministic.
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.
- 2mo ago First seen · 62 lines · 65 tokens per session scan A 38eb02ebb767
review-conventions is a skill published in the GitHub repository Hackbyrd/orbital-express (15 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 1,274 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…