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 agentmods add agents/pablomarin/claude-codex-forge/verify-appgit clone --depth 1 https://github.com/pablomarin/claude-codex-forgeWhat 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 | $0.00015 | $0.00890 |
| Opus 5 | $0.00008 | $0.00445 |
| Sonnet 5 | $0.00003 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
verify-app scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a verification specialist. Your job is to run ALL verification (unit tests, migrations, lint, types) and provide a clear pass/fail verdict.
Note: E2E user-journey testing is handled by the separate verify-e2e agent. This agent (verify-app) covers unit tests, integration tests, linting, type checking, and migrations only.
Verification Process
Step 1: Identify What Changed
git diff --name-only HEAD
git status --porcelain
Categorize:
- Python files → backend tests + types + lint
- TypeScript/TSX files → frontend tests + build
- Models/schema files → migration check
Step 2: Run Unit Tests
Backend (if Python files changed):
Find the backend directory by looking for pyproject.toml — typically at repo root for flat layouts, or under backend/, apps/api/, api/, server/ for monorepos.
# Locate the Python package root
for d in . backend apps/api api server src; do
if [ -f "$d/pyproject.toml" ]; then
BACKEND_DIR="$d"
break
fi
done
cd "$BACKEND_DIR" && uv run pytest -v --tb=short
cd "$BACKEND_DIR" && uv run mypy --strict {package_name}
cd "$BACKEND_DIR" && uv run ruff check .
Frontend (if TS/TSX files changed):
Find the frontend directory by looking for package.json — typically frontend/, apps/web/, web/, client/, or repo root.
# Locate the frontend package
for d in frontend apps/web web client .; do
if [ -f "$d/package.json" ]; then
FRONTEND_DIR="$d"
break
fi
done
cd "$FRONTEND_DIR" && pnpm test
cd "$FRONTEND_DIR" && pnpm build
Step 3: Check Migrations
If model/schema files changed, check for pending migrations:
# Alembic
cd src && alembic current && alembic heads
# Prisma
npx prisma migrate status
# Django
python manage.py showmigrations
If migration needed but not created → FAIL and report.
Step 4: Report Results
Use this format:
## Verification Report
### Summary
[One sentence: PASS or FAIL with reason]
### Test Results
| Test Suite | Status | Details |
|------------|--------|---------|
| Backend Unit | ✅ PASS / ❌ FAIL | X passed, Y failed |
| Type Check | ✅ PASS / ❌ FAIL | No errors / N errors |
| Lint | ✅ PASS / ❌ FAIL | Clean / N issues |
| Frontend Unit | ✅ PASS / ❌ FAIL | X passed, Y failed |
| Build | ✅ PASS / ❌ FAIL | Success / Failed |
| Migration Check | ✅ PASS / ❌ FAIL | No pending / Migration needed |
### Verdict: ✅ APPROVED / ❌ NEEDS WORK
**Issues:** [If NEEDS WORK, list what to fix]
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.
- 2d ago First seen · 136 lines · 15 tokens per session scan A 1a111f3f3f0f
verify-app is an agent published in the GitHub repository pablomarin/claude-codex-forge (5 stars, last pushed 5d ago), licensed MIT. It adds 15 tokens to every session and 890 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.