A free, open-source CLI and GitHub Action. After your AI review, farol tells the person who approves how risky the merge is and which files carry the risk, so the riskiest changes get the most attention.
Website · Live demo · Get started · Reference
Agents write the code and agents review it. The last call is still a person's: approve the merge or not. That approval is the scarce part, and spread evenly over every pull request it turns into a skim, which is how a one-line change to a shared hook takes down forty pages.
farol comes after the AI review, not instead of it. Your review agent comments on the lines in the diff. farol gives the person who approves what the agent cannot reliably give: the risk of accepting the change, and where it lives. The goal is not only a faster review: low-risk pull requests can go fast, and the risky ones get read line by line, starting with the files that carry the risk. It works from static analysis (the compilers' own view of your code, not a model's guess), so the same pull request always gets the same answer.
The Claude Code team describes the same principle in How the Claude Code team does code review: review effort follows the risk of the change. As they put it, "The change sets the tier, not the author."
farol (Portuguese for lighthouse) does the triage before the reviewer opens the diff:
- What does this change reach? Every existing page, API operation, RPC method, job and script that runs the changed code, with the call chain to each.
- How risky is the merge? A verdict (fast track, quick review, careful review) and a 0–100 risk score from reach, diff coverage, security findings, contract breaks and dependency changes.
- Where do I start? The riskiest files first, with inline diffs, untested lines marked, and a checklist of what to try by hand.
Free and open source (MIT). Run it as a CLI with npx @winninjs/farol
, or on every pull request with the GitHub
Action winnin/farol/action
. No account, no hosted service: it runs on your machine or in your CI runner, comments on
every PR and never blocks a merge. It never executes your code and never sends it anywhere.
See farol on a real pull request →
The demo holds the reports farol produced in CI for a pull request on the FastAPI full-stack template: a FastAPI backend and a React frontend with TanStack Router. The pull request adds a status to items and an Insights page, with the kind of problems a reviewer should catch: a breaking API change, SQL built with an f-string, a shared component without tests.
- Backend report: ⚠ careful review, a breaking contract change and a high-severity security finding.
- Frontend report: ⚠ careful review, a new page and the existing pages a shared component reaches.
The reports are interactive: mark files as reviewed, mark a page as behind a feature flag, open the inline diffs,
follow the test plan and copy the review record from the Result tab. They are the same files the pull request's
comments link to (the pull request); the
copies live in docs/demo/
.
AI review agents | farol | |
---|---|---|
Reads | the diff, and whatever context fits in the prompt | the whole program at the base and the head, with the compilers (TypeScript type checker, go/types , Python ast ) |
Tells you | what may be wrong in these lines | what these lines reach, how risky the merge is, and where to look first |
Answers are | probabilistic: worded differently on every run | deterministic: the same PR gives the same report, and every claim comes with its call chain |
When unsure | may sound confident anyway | says unknown and asks for a careful review |
Runs | a model, usually a hosted service | locally or in your CI: it never executes your code and never sends it anywhere |
Use both, in that order. The agent reviews the lines first; then farol tells the person who approves how much attention the merge needs, which files deserve it, which pages and endpoints to test by hand and which contract changes need their clients checked. The agent's review is not enough exactly when a small change has a large reach, and that is what farol shows.
- Review attention goes where the risk is. A 40-file PR usually has two or three files that can actually hurt. farol ranks them, so the reviewer reads those closely and skims the rest with a clear conscience.
- It follows the code, not the file names. farol builds a declaration graph with the real compilers (the TypeScript type checker,
go/types
, Python'sast
). A change toformatPrice
lists the twelve pages that render it, not "1 file changed". - Contract breaks are caught before clients are. Removed response fields, new required parameters, changed types in GraphQL, FastAPI, Go handlers and gRPC, with the services that call each endpoint.
- Review the whole PR, or just what changed since your last look. Every push gets two reports: the full pull request, and only the commits since the previous push. After a round of fixes, the reviewer checks the new commits instead of starting over.
- It uses what your CI already has. Coverage, lint, security and audit reports become diff coverage and findings on the changed lines. Nothing runs twice.
- Fail closed. When farol cannot read part of a change, it says so (
unknown
) and asks for a careful review. It never calls something safe because it did not understand it. - Built for the human in the loop. Mark files as reviewed, mark pages as behind a feature flag, check off findings, and paste the result back in the PR as a record of what was reviewed.
- Live demo
- farol after your AI review
- Get started
- Recipes: React Router · Next.js · TanStack Router · TypeScript API · Go · Python · Datadog
- What is supported
- Reading the review
- How it works · Security · Limitations · FAQ
- Reference (every command, option and configuration key)
You need Node.js 22+ and git (plus go
for Go projects, python3
3.11+ for Python ones). Nothing to
install: run farol with npx @winninjs/farol
.
1. Describe your project in a farol.config.json
at its root. One line is enough to start; pick your stack:
Your project | farol.config.json |
Full recipe |
---|---|---|
React app with React Router | { "routes": { "file": "src/routes.tsx" } } (the file that builds the route table) |
React Router |
Next.js app (Pages or App Router) | { "routes": { "adapter": "next" } } |
Next.js |
React app with TanStack Router | { "routes": { "adapter": "tanstack-router", "dir": "src/routes" } } |
TanStack Router |
TypeScript API (GraphQL, REST) | { "surface": "backend" } |
TypeScript API |
Go service | { "language": "go", "surface": "backend" } |
Go |
Python service (FastAPI, Flask, Django, Celery…) | { "language": "python", "surface": "backend" } |
Python |
2. Check what farol sees: the pages, endpoints, jobs and scripts it found.
npx @winninjs/farol routes
3. Analyze a branch against its target and open the report.
npx @winninjs/farol analyze --base origin/main --head HEAD --out farol.json
npx @winninjs/farol html --in farol.json --out farol.html && open farol.html # xdg-open on Linux
cd path/to/your/react-app
echo '{ "routes": { "file": "src/routes.tsx" } }' > farol.config.json
npx @winninjs/farol routes # lists your pages: "/", "/products", "/settings"…
git checkout my-feature-branch
npx @winninjs/farol analyze --base origin/main --head HEAD --out farol.json
npx @winninjs/farol html --in farol.json --out farol.html && open farol.html
The report already shows the verdict, the score, the files to start with, the pages the change reaches and what to test by hand. Next steps: add your coverage, lint and audit reports and run farol on every PR with the recipe for your stack. Every option is in the reference and, per stack, in examples/README.md.
Running it often?
npm install --global @winninjs/farol
gives you a plainfarol
command.
Each recipe has three parts: the farol.config.json
to commit, the reports to produce, and the GitHub Actions
workflow. The workflows in examples/
are complete and share one shape:
tests
runs your tests, linter and audit and keeps the reports. It runs the PR's code, so it has no secrets and a read-only token. If you already have a test job, keep it and add its upload step.farol
runs after it (pass or fail), reads git and the reports, and posts a new comment on every push with a link that opens the HTML report in the browser, plus a second report with only the commits since the previous push. It never runs the PR's code.- Drafts are skipped, fork PRs get no comment (their token is read-only), and every farol step is
continue-on-error
.
Pin the action to a commit once it works for you: winnin/farol/action@<sha> # main as of <date>
.
examples/README.md
goes deeper for each stack: every configuration key, CLI parameter and
action input, and how to check a setup.
React Router route tables (object and JSX forms, lazy routes, split route modules), reach per declaration.
{
"routes": { "file": "src/routes.tsx" },
"roles": { "global": ["src/main.tsx", "src/App.tsx", "src/styles/global.css", "package.json", "vite.config.ts"] }
}
npx vitest run --coverage.enabled --coverage.reporter=json --coverage.reportsDirectory=reports/coverage
npx eslint -f json -o reports/eslint.json <changed files>
npm audit --json > reports/audit.json # or pnpm audit --json
npx @winninjs/farol analyze --base origin/main --head HEAD \
--coverage reports/coverage/coverage-final.json --eslint reports/eslint.json --audit reports/audit.json --out farol.json
CI: copy examples/workflow.yml
to .github/workflows/farol.yml
.
Set coverage.include: ['src/**/*.{ts,tsx}']
in the Vitest config so files no test loads are reported as untested.
Split route trees go in routes.extraFiles
; a fuller config is in examples/farol.config.json.
Pages Router and App Router: every page, API route, layout, _app
/_document
and middleware, read from the file
names. Dynamic segments ([id]
), catch-alls, route groups and parallel slots are understood.
{
"routes": { "adapter": "next" },
"roles": { "global": ["next.config.*", "package.json"] }
}
pages/
and app/
are found in the project or in its src/
; set "dir"
when they live elsewhere. Reports and CI
are the same as for React Router (Jest or Vitest coverage, ESLint, audit). In a
monorepo whose tsconfig extends a workspace package ("extends": "tsconfig/nextjs.json"
), install dependencies
before analyzing, so the package is in node_modules
.
File-based routing: every module calling createFileRoute('<id>')
under the routes directory, with the root route,
pathless layouts (_app
) and parent routes as layouts of their children.
{ "routes": { "adapter": "tanstack-router", "dir": "src/routes" } }
Reports and CI are the same as for React Router.
GraphQL root operations (schema files and gql
templates, per resolver) and Fastify/Express-style REST endpoints.
{
"surface": "backend",
"backend": { "graphql": true, "rest": true },
"roles": { "global": ["package.json", "src/app.ts"] }
}
Reports and CI are the same as for React Router: examples/workflow.yml
. If
resolvers reach data through an injected context (ctx.loaders.Brand.byId()
), tell farol where the providers live:
"backend": { "context": { "loaders": ["src/modules/*/loaders/index.ts"] } }
.
chi, gin, echo and net/http routes, gRPC service methods and main
binaries, reach per declaration with interface
calls resolved to their implementations.
{ "language": "go", "surface": "backend" }
go test -coverpkg=./... -coverprofile=reports/cover.out ./...
golangci-lint run --output.json.path=reports/golangci.json --issues-exit-code=0 ./... # enable gosec
govulncheck -json ./... > reports/govulncheck.json
npx @winninjs/farol analyze --base origin/main --head HEAD \
--coverage reports/cover.out --eslint reports/golangci.json --audit reports/govulncheck.json --out farol.json
CI: copy examples/workflow-go.yml
. farol reads modules offline, so the workflow runs
go mod download
for the base and the head first.
FastAPI and Flask routes (routers, blueprints, prefixes), Django URLs, MCP tools/resources/prompts, Celery tasks,
Temporal workflows and activities, Prefect flows and __main__
scripts. farol parses your code; it never imports it.
{ "language": "python", "surface": "backend", "python": { "roots": ["src", "."] } }
pytest --cov=src --cov-report=json:reports/coverage.json
ruff check --output-format json --extend-select S --exit-zero . > reports/ruff.json # S = flake8-bandit
pip-audit --format json -o reports/pip-audit.json
npx @winninjs/farol analyze --base origin/main --head HEAD \
--coverage reports/coverage.json --eslint reports/ruff.json --audit reports/pip-audit.json --out farol.json
CI: copy examples/workflow-python.yml
(uses uv
; swap in your installer).
Optional, and information only: it never changes the score. With it the report shows how much traffic each affected page or operation gets, its distinct production errors (linked to Datadog), the changed files that already throw errors, and the services that call each changed endpoint.
{
"datadog": {
"env": "prod",
"rum": { "applicationId": "<RUM application id>" },
"apm": { "service": "orders-api", "operations": ["fastapi.request"] }
}
}
DD_API_KEY=… DD_APP_KEY=… npx @winninjs/farol usage --out usage.json # last 14 days
npx @winninjs/farol analyze … --usage usage.json
CI: the example workflows have a farol-usage
job: set the DD_API_KEY
and DD_APP_KEY
secrets and the
repository variable FAROL_DATADOG=true
. It reads Datadog once a day and never sees the PR's code. Keys, scopes and
matching rules are in the reference.
TypeScript / React frontends | TypeScript / JavaScript backends | Go | Python | |
---|---|---|---|---|
Entry points | React Router route tables (object and JSX forms, lazy routes, split route modules); Next.js Pages and App Router (pages, API routes, layouts, middleware); TanStack Router file-based routes | GraphQL root operations (schema files and gql templates) and REST endpoints (Fastify/Express style) |
chi, gin, echo and net/http routes; gRPC service methods; main binaries |
FastAPI and Flask routes (routers, blueprints, prefixes); Django URLs; MCP tools, resources and prompts; Celery tasks; Temporal workflows and activities; Prefect flows; __main__ scripts |
Reach precision | per declaration (TypeScript type checker) | per module, per resolver for GraphQL | per declaration (go/types , interface calls resolved to implementations) |
per declaration (Python ast with local type inference) |
Contract changes | — | GraphQL schema (breaking / dangerous / safe) | Handler request and response types (net/http, chi, gin, echo); gRPC messages | FastAPI parameters, body, response and Pydantic models |
Dependencies | package.json + npm/pnpm/yarn/bun lockfiles |
same | go.mod + go.sum |
pyproject.toml (PEP 621, extras, groups, uv, Poetry), requirements.txt + uv.lock /poetry.lock /Pipfile.lock |
Diff coverage | Istanbul coverage-final.json (Vitest, Jest) |
same | go test -coverprofile |
coverage.py JSON (pytest --cov ) |
Lint | eslint -f json |
same | golangci-lint JSON | ruff JSON |
Security | built-in rules (XSS sinks, eval , hard-coded secrets, javascript: URLs…) |
same | gosec (through golangci-lint) | flake8-bandit (ruff S rules) |
Vulnerabilities | npm audit --json , pnpm audit --json |
same | govulncheck -json |
pip-audit --format json |
Suppressions | eslint-disable , @ts-ignore , @ts-expect-error , as any … |
same | //nolint , //lint:ignore , #nosec |
# noqa , # type: ignore , # nosec , # pragma: no cover … |
Traffic and errors (optional) | Datadog RUM page views and errors | Datadog APM requests, error spans and callers | same | same |
In every language: environment, infrastructure and CI files (.env*
, Dockerfiles, compose, CI pipelines, helm, k8s,
terraform…) in a section of their own; incremental analysis since any commit (--since
); suggested reviewers from
git blame and CODEOWNERS; reports as a GitHub comment, Markdown or a single-file HTML page.
farol produces two things: a PR comment with the verdict, the top files and a test checklist, and a single-file HTML report (linked from the comment) where the review happens. Here is what each part is for and how to use it.
What it tells you is how much of your time the PR deserves.
Verdict | Means | What to do |
---|---|---|
✓ Fast track | Only new code, tests or low-risk changes. | Skim the diff and approve. |
◐ Quick review | Existing code changed in a contained way, or a weaker signal (low coverage, lint errors, a config file). | Check the Start here files, then approve. |
⚠ Careful review | Wide or silent breakage is possible: a score of 60+, a breaking contract change, a high-severity finding, an untested central file, or code farol could not read. | Read the Start here files line by line and test what they reach. |
The score (0–100) is the chance that at least one risky item breaks something. Expand What adds to it to see each item and its points: the files by reach × untested share, findings, contract changes, dependencies. The verdict always comes with its reasons; read them before the diff.
The changed code files, riskiest first. Each row shows how many existing pages or operations run the file, its diff coverage, its findings and its own risk points; with Datadog, also its traffic and production errors. Open the inline diff: added lines no test runs are marked ○, lines with findings ⚠.
How to use it: review top-down and tick Mark as reviewed on each file. The score drops as you go, so you always know how much risk is left. Below it come the low-risk files to skim, environment/infrastructure/CI files (check their values per environment), and files that need no review (docs, lockfiles, tests).
On every page or operation row, and in a panel at the top: mark an entry point that is entirely behind a flag. Files that only flagged entry points use leave the review, labeled behind a flag rather than reviewed. Use it for work-in-progress features shipped dark, so the remaining score reflects what users will actually hit.
Every new and affected entry point, as a list or a tree by module. Opening one draws how the change reaches it, file by file. With Datadog each one shows its traffic share and its distinct errors, busiest first. Use it to judge blast radius: a change reaching 3 rarely used admin pages is not the same as one reaching the checkout.
Each endpoint whose request or response shape changed, as breaking (clients built for the base can fail), dangerous (they may misbehave) or safe (compatible additions), with the exact field and the calling services from Datadog. Use it to confirm every breaking change is intended and its clients are updated, then tick checked with clients.
The evidence behind the score: security findings on the changed lines (with a checked box each), added or bumped dependencies with known vulnerabilities, and diff coverage per file. A report that was not given shows as not verified, never as passing.
The new and affected pages or operations to try by hand, new ones first, then by the risk of the file that reaches them. The PR comment has it as a task list. Use it when you run the branch locally or on a preview environment. It follows your review: once every changed file behind an item is marked as reviewed, the item is marked too (✓ files reviewed), or 🚩 behind a flag. Its own checkbox, for the manual test, stays yours to tick.
Who should review: the people who wrote the code this PR changes (git blame, weighted by each file's risk), plus CODEOWNERS. The PR's own authors and bots are left out, and inactive people are labeled. Use it to request the person who knows the riskiest file, not just whoever is free.
A Markdown record of the review: the initial verdict and score, the score left now, the flagged entry points, the reviewed files, and the checked findings and contract changes. Copy as Markdown and paste it in the PR as your review comment, so the next person knows what was looked at.
After a push to an open PR, the comment carries a second report with only the commits since the previous push
(analyze --since <sha>
; after a force-push, from its merge-base). Its verdict, score and Start here cover just
those changes. Use it for the second round of a review: check that the fixes do what was asked and nothing
else, then go back to the full report only if the new commits reach somewhere new.
Kept in Details and a collapsed block of the comment, so reviewers form their own opinion first:
isolated
(only adds), touches-existing
(existing code changed), global
(a global file, manifest or critical
dependency) and unknown
(part of the change could not be read: never safe). Every reason code is in
docs/reasons.md.
- Diff the merge-base and the head, detecting renames and ignoring whitespace-only and trailing-comma lines.
- Read both trees without running anything: the TypeScript compiler API,
go list
+go/types
(offline), Pythonast
. From them, the entry points and a graph of which declaration uses which. - Compare declarations by a hash of their code, so comments and formatting never count. New declarations and entry points are additive.
- Reach: from each changed declaration to every entry point that runs it, keeping the shortest chain.
- Classify, weigh and plan: class, score, verdict, files to start with, test checklist.
On 662 past commits of four repositories, fast track had 0 problems in 56 commits and the score's AUC was
0.72–0.83; run farol calibrate
on your own history.
The details per language are in docs/how-it-works.md, and the reasons behind every choice in
docs/DECISIONS.md.
analyze
never executes code of the analyzed repository and never uses the network. The Go and Python helpers use only their standard libraries and only parse.- Only
comment
(GitHub API) andusage
(Datadog API) talk to the network. Error messages are not copied from Datadog, only error types. - In CI the job that runs your code has no secrets and no write token; the job that comments never runs your code.
- Shadow mode: farol informs, it never approves, requests changes or fails a check.
- Static reading: values built at runtime are invisible (computed route paths,
getattr
,importlib
, DI containers, registries filled in loops). When an entry point cannot be read, the PR isunknown
; when a call cannot be resolved, farol assumes it reaches more, never less. - TypeScript frontends: React Router, Next.js and TanStack Router (file-based) only: no code-based TanStack route trees, Remix/React Router file conventions, Vue or Svelte. JavaScript files, renamed files and TypeScript backends use module-level reach.
- Go: route prefixes from middleware stacks other than chi/gin/echo groups are not applied, and project types that wrap a router with their own registration API (Gitea's
web.Router
) are not read. Python: Django REST Framework routers are not read. - The score and verdict thresholds are heuristics checked on a few repositories. Calibrate them on yours.
We already have an AI reviewer. Why add farol? They answer different questions. The agent comments on the lines in the diff; after it, farol tells the person who approves how risky the merge is and which files carry the risk, from static analysis of the whole program. Run both: farol's comment and report sit next to the agent's, and neither blocks the merge.
Is it free? Yes. farol is open source under the MIT license, with no account, hosted service or paid tier: run it
with npx @winninjs/farol
or the GitHub Action winnin/farol/action
.
Will it slow down CI? No. farol runs after your tests and reuses their reports. The analysis takes about 3 s for a 300-file Python service, 8–10 s for a large TypeScript monorepo or a Go service with a cold cache, and under a second for the base when its helper output is cached.
Can I use it outside GitHub? Yes. analyze
, html
and report
work anywhere; only comment
is
GitHub-specific. Post the output of npx @winninjs/farol report
with your platform's API.
The report says "not verified". That report was not given, or the path is wrong. Paths given to analyze
are
relative to the current directory; paths in farol.config.json
are relative to the project.
A page I changed is not listed. Run npx @winninjs/farol routes
to see the entry points farol reads, and
npx @winninjs/farol impact <file>
to see what reaches a file. Unreadable route constructs are listed under diagnostics.
Go: "farol reads Go modules offline: run go mod download". The module cache lacks a dependency of the base or the
head. Run go mod download
for both before analyzing.
Monorepo? Point --cwd
at the app. Paths stay relative to the repository root, and changes in apps the project
does not use are listed as outside it.
Contributions are welcome: route adapters, frameworks, languages, report formats and better heuristics. See CONTRIBUTING.md for the setup, the architecture and the conventions, and SECURITY.md to report a vulnerability.
MIT © 2026 Winnin