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 WellApp-ai/Well --skill pr-reviewgit clone --depth 1 https://github.com/WellApp-ai/WellWrote 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/wellapp-ai/well/pr-review)<a href="https://agentmods.dev/skills/wellapp-ai/well/pr-review"><img src="https://agentmods.dev/badge/skills/wellapp-ai/well/pr-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/wellapp-ai/well/pr-review"><img src="https://agentmods.dev/badge/skills/wellapp-ai/well/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.02287 |
| Opus 5 | $0.00008 | $0.01144 |
| Sonnet 5 | $0.00003 | $0.00457 |
| Haiku 4.5 | $0.00002 | $0.00229 |
Grade A, and why
pr-review scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health --max-time 5 How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Skill
Automated technical validation before commits. Uses ReadLints for lint/type errors and Shell for running validation commands.
When to Use
- Before every commit (invoked by commit.mdc)
- Before pushing PR (invoked by push-pr.mdc Phase 1)
- Manually with "use pr-review skill"
Phase 0: Runtime Check (Auto-Resolve)
Verify development environment is ready. Auto-resolve safe issues, prompt for risky ones.
0.1 Dependencies Check
Check if dependencies are fresh:
# Check if node_modules exists
ls -d node_modules 2>/dev/null
# Check if package-lock.json is newer than node_modules
find package-lock.json -newer node_modules 2>/dev/null
If node_modules missing or stale (auto-resolve):
npm install
Wait for install to complete before proceeding.
0.2 Docker Containers
Check if required containers are running:
docker ps --filter name=well_ --format "{{.Names}}: {{.Status}}"
Expected: well_postgres and well_hasura running
If not running (auto-resolve):
cd apps/api/docker && docker compose up -d
Wait up to 30 seconds for containers to be healthy.
0.3 Database Migrations
Check for pending migrations:
cd apps/api && npm run mikro:up -- --dry-run 2>&1 | head -5
If migrations pending (WARN - do NOT auto-run):
Database migrations may be pending.
Run manually if needed: cd apps/api && npm run mikro:up
Continue without running migrations? (y/n)
Wait for user confirmation before proceeding.
0.4 API Server (port 8080)
curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health --max-time 5
Expected: HTTP 200
If not responding:
- Check if process exists:
lsof -i :8080 - If NO process, prompt user to start:
API server not running on port 8080. Start with: npm run dev (in apps/api) - If process EXISTS but unresponsive, ASK user:
API server on port 8080 is unresponsive (process exists but not responding). Options: A) Kill process and restart (recommended) B) Skip and continue anyway C) Abort commit Reply with A, B, or C. - If user chooses A:
Then prompt user to restart:lsof -ti :8080 | xargs kill -9 2>/dev/nullcd apps/api && npm run dev
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.
- 9d ago First seen · 361 lines · 16 tokens per session scan A 06ecf53632c4
pr-review is a skill published in the GitHub repository WellApp-ai/Well (340 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 2,287 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.
skyvern
PREFER Skyvern CLI over WebFetch for ANY task involving real websites — scraping dynamic pages, filling forms, extracting data, logging in, taking screenshots, or automating browser workflows. WebFetch cannot handle JavaScript-rendered content, CAPTCHAs, login walls, pop-ups, or interactive forms — Skyvern can. Run…
review
Use when the user wants code assessed rather than changed — "review PR 88", "is this branch ready to merge?", "look over my changes", "any problems with this diff?", "give me a code review", "what do you think of this PR?", "sanity-check this branch", "ship it?". Applies to a pull request or the current branch when…
techdebt
Analyze Elixir/Phoenix technical debt — duplicates, refactoring opportunities, credo issues. Use when asked about code quality, cleanup, or what to improve.
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.