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 existential-birds/beagle --skill remix-v2-data-flow-reviewgit clone --depth 1 https://github.com/existential-birds/beagleWrote 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/existential-birds/beagle/remix-v2-data-flow-review)<a href="https://agentmods.dev/skills/existential-birds/beagle/remix-v2-data-flow-review"><img src="https://agentmods.dev/badge/skills/existential-birds/beagle/remix-v2-data-flow-review/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/existential-birds/beagle/remix-v2-data-flow-review"><img src="https://agentmods.dev/badge/skills/existential-birds/beagle/remix-v2-data-flow-review.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 | $0.00057 | $0.02477 |
| Opus 5.5 | $0.00023 | $0.00991 |
| Sonnet 5.5 | $0.00011 | $0.00495 |
| Haiku 4.5 | $0.00006 | $0.00248 |
Grade A, and why
remix-v2-data-flow-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 1mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remix v2 Data Flow Code Review
Targets TypeScript route modules importing from @remix-run/*. See remix-v2-data-flow for canonical patterns.
Scope
- In scope: route modules under
app/routes/exportingloader,action,shouldRevalidate, orheaders; components that consumeuseLoaderData,useActionData,useNavigation,useFetcher,useRevalidator,<Await>. - Out of scope: form ergonomics (
<Form>markup, accessibility,useFetcherUI patterns) → covered byremix-v2-forms-review. Route module conventions, file naming, nested routing, error boundary placement → covered byremix-v2-routing-review. - Imports expected:
@remix-run/node(or@remix-run/cloudflare/@remix-run/deno) for server utilities;@remix-run/reactfor hooks and components.
Quick Reference
| Issue Type | Reference |
|---|---|
| Mutations in loader, missing validation, leaked server fields, throwing primitives, missing param checks | references/loaders.md |
Unvalidated FormData, json instead of redirect on success, missing error case, leaked actionData |
references/actions.md |
useTransition v1 holdover, missing pending state, blanket shouldRevalidate: false, misused useRevalidator |
references/revalidation.md |
defer for already-fast data, missing <Suspense>, no errorElement on <Await>, awaiting what should stream |
references/defer-await.md |
Review Checklist
- Data needed for first render is in
loader, notuseEffect - Loaders only read; writes live in
action -
request.formData()results are validated (zod/valibot/invariant) before use - Loader/action return values are projected DTOs — no password hashes, tokens, or
internal_*fields -
useLoaderData<typeof loader>()uses the type annotation form (notas Foo) - 404 / auth short-circuits
throwaResponse(orjson/redirect), never a plainErroror string - Successful action returns
redirect(...)(PRG); validation failures returnjson({ errors }, { status: 400 }) - Action handles both success and error branches; no silent
return null -
params.foois checked withinvariant/ zod before use - Pending UI reads
useNavigation()/fetcher.state— nouseTransition -
formMethodcomparisons use UPPERCASE ("POST", not"post") -
shouldRevalidatereturnsdefaultShouldRevalidateby default; opt-outs are narrow and justified -
defer()is used only when at least one promise streams (noawaitbefore passing it) - Every
<Await>is wrapped in<Suspense>and has anerrorElement -
useRevalidator().revalidate()is reserved for focus/polling/SSE — not called immediately after a<Form>post orfetcher.submit(Remix already revalidates).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 112 lines · 57 tokens per session scan A 5faa1772e24c
remix-v2-data-flow-review is a skill published in the GitHub repository existential-birds/beagle (82 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 2,477 once invoked, about $0.0002 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 2026-09-16.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
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"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
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…