Finance

stripe-reconcile - Claude MCP Skill

Fix issues found by stripe-audit. Reconciles configuration drift, fixes code patterns, and resolves discrepancies.

SEO Guide: Enhance your AI agent with the stripe-reconcile tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to fix issues found by stripe-audit. reconciles configuration drift, fixes code patterns, and resolves ... Download and configure this skill to unlock new capabilities for your AI workflow.

🌟1 stars • 1 forks
📥0 downloads

Documentation

SKILL.md
# Stripe Reconcile

Fix issues identified by the audit.

## Branching

Assumes you start on `master`/`main`. Before making code changes:

```bash
git checkout -b fix/stripe-reconcile-$(date +%Y%m%d)
```

Configuration-only changes (env vars, dashboard settings) don't require a branch. Code changes do.

## Objective

Take audit findings and fix them. Configuration issues get fixed directly. Code issues get delegated to Codex.

## Process

**1. Triage Findings**

From the audit report, categorize:

**Configuration fixes** (do directly):
- Missing env vars
- Wrong webhook URL
- Dashboard settings

**Code fixes** (delegate to Codex):
- Missing trial_end handling
- Idempotency implementation
- Access control corrections

**Design issues** (may need stripe-design):
- Wrong checkout mode
- Missing webhook events
- Architectural problems

**2. Fix Configuration**

For env var issues:
```bash
# Example: missing prod webhook secret
npx convex env set --prod STRIPE_WEBHOOK_SECRET "whsec_..."
```

For webhook URL issues:
- Update in Stripe Dashboard
- Or use Stripe CLI: `stripe webhook_endpoints update <id> --url "https://..."`

Verify fixes immediately.

**3. Delegate Code Fixes to Codex**

For each code issue, create a focused Codex task:

```bash
codex exec --full-auto "Fix: [specific issue from audit]. \
Current code in [file]. Problem: [what's wrong]. \
Fix: [what it should do]. Reference [pattern file] for correct approach. \
Run pnpm typecheck after." \
--output-last-message /tmp/codex-fix.md 2>/dev/null
```

Then review: `git diff --stat && pnpm typecheck`

**4. Verify Each Fix**

After fixing, verify:
- Configuration: `npx convex env list --prod | grep STRIPE`
- Webhook URL: `curl -I -X POST <url>`
- Code: `pnpm typecheck && pnpm test`

**5. Re-audit**

After all fixes, run a quick re-audit to confirm issues resolved.

## Common Fixes

**Missing env var on prod**
```bash
npx convex env set --prod STRIPE_WEBHOOK_SECRET "$(printf '%s' 'whsec_...')"
```
(Use printf to avoid trailing newlines)

**Webhook URL redirect**
Update to canonical domain in Stripe Dashboard. If `example.com` redirects to `www.example.com`, use `www.example.com`.

**Missing trial_end handling**
In checkout session creation, calculate remaining trial and pass to Stripe:
```typescript
const trialEnd = user.trialEndsAt && user.trialEndsAt > Date.now()
  ? Math.floor(user.trialEndsAt / 1000)
  : undefined;
// Pass in subscription_data.trial_end
```

**Missing idempotency**
Store `lastStripeEventId` on user, check before processing webhook.

## Output

For each finding:
- What was fixed
- How it was fixed
- Verification result

Any remaining issues that couldn't be auto-fixed.

Signals

Avg rating0.0
Reviews0
Favorites0

Information

Repository
phrazzld/claude-config
Author
phrazzld
Last Sync
3/2/2026
Repo Updated
3/1/2026
Created
1/23/2026

Reviews (0)

No reviews yet. Be the first to review this skill!

Related Skills

firecrawl-build-search

Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.

35092

firecrawl-build-onboarding

Get Firecrawl credentials and SDK setup into a project. Use when an application needs `FIRECRAWL_API_KEY`, when an agent should add Firecrawl to `.env`, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill includes its own browser auth flow, so it does not depend on the website onboarding skill.

35092

firecrawl-build

Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl explicitly and only describes wanting web data, website content, search, scraping, or interaction in an application. Trigger for Firecrawl requests, "fire girl" shorthand, and generic app-level web-data needs that should map to `/scrape`, `/search`, or `/interact`. Do not use this skill for one-off terminal-only web tasks during the current session; use `firecrawl/cli` for those.

35092

firecrawl-build-interact

Integrate Firecrawl `/interact` into product code for dynamic pages and browser actions after scraping. Use when a feature needs clicks, form fills, pagination, authentication-aware flows, or other multi-step interactions that plain `/scrape` cannot complete.

35092

Related Guides