building in public

inprod

developer tools for shipping code that actually works in production

the reality layer for AI-generated code

7 toolsAI-nativeproduction-first

AI code lives in a probabilistic world — tokens, predictions, completions. but production lives in a deterministic world — it compiles or it doesn't, tests pass or they fail, it handles 10k users or it crashes, an attacker gets in or they don't. these tools are the bridge between those two worlds. the convergence point where AI-generated code meets hard reality and either survives or gets hardened until it does.

the toolkit

merlyn

live

tells you your next prompt

a local development coach and MCP server. guides developers through plan, build, ship, and grow phases with AI-powered analysis and smart prompt suggestions. orchestrates the entire inprod tool suite at the right moment in the lifecycle. pure methodology, zero cloud.

$npx merlyn-mcp@latest

slopometer

in development

finds the bugs and slop in your code before you ship

CVE scanning via OSV, anti-pattern detection across languages, hallucinated package detection, dead code identification, complexity analysis, and a binary ship/no-ship verdict. the pre-commit gut check.

$npx slopometer scan .

orion

live

tells you what's missing before production breaks

scores production readiness across 12+ categories and estimates max concurrent users. checks for rate limiting, connection pooling, structured logging, monitoring, alerting, health endpoints, CI/CD, and everything else you forget until it's too late.

$npx orion-archi .

pinata

live

generates adversarial tests that target your code's specific security gaps

reads your source code, identifies risk patterns via AST analysis, and generates runnable test files. SQL injection, XSS, auth bypass, path traversal, input validation -- pinata writes the tests that try to break your code. not a scanner. a test generator.

$npx pinata .

whackamole

in development

attacks your running app, fixes what it breaks, hardens the whole class

dynamic security hardening. sends real attack payloads to your running app, proves exploits with evidence, generates AI fixes, and verifies fixes blindly. then identifies every endpoint with the same vulnerability class and applies architectural fixes. loop until equilibrium.

$npx whackamole attack

crowbar

in development

autonomous external pentest with zero source code knowledge

give it a URL. it crawls, fingerprints, discovers hidden endpoints, evades WAFs, and attacks with 20+ exploit plugins. zero prior knowledge. separate verification agent confirms every finding. full proof-of-concept reports with curl commands. the external attacker you hire, automated.

$npx crowbar scan https://yoursite.com

convergence

live

proves AI-generated fixes are correct, not just test-passing

blind verification engine. the AI that generated the fix never sees the test implementations. it receives only pass/fail per domain -- safety, security, efficiency, functionality. iterates until all domains converge. generates compliance-ready audit trails for FDA, FINRA, and CMMC.

$pip install convergence

fossilize

in development

documentation derived from running your code

builds a scope graph of your codebase via tree-sitter, maps tests to functions, overlays coverage data. every claim traceable to a line of code or a passing test. drift detection catches when code changes but docs don't. the verification index for agents, auditors, and compliance.

$npx fossilize .

the pipeline

from idea to production-hardened code

1
merlyncoach

tells you what to do next, orchestrates the suite

2
slopometerscan

finds bugs, bad patterns, hallucinated packages

3
orionscore

checks what's missing from your infrastructure

4
pinatagenerate tests

writes adversarial tests targeting your specific gaps

5
whackamoleharden

attacks your running app, fixes and hardens

6
crowbarpentest

autonomous external pentest, zero source code

7
convergenceverify

proves fixes are correct via blind testing

8
fossilizedocument

generates evidence-backed docs from what survived

philosophy

attack before you ship

every tool in the suite is designed to find problems before users do. adversarial testing, blind verification, black-box pentesting. if your code survives this gauntlet, it survives production.

fixes, not warnings

warnings are noise. every tool generates actionable fixes, runnable tests, or verified patches. the goal is code that works, not a report that sits in a drawer.

AI-native, human-directed

AI generates the code. AI attacks the code. AI fixes the code. but humans set the direction, define the properties, and make the decisions. the tools encode methodology, not just capability.

cheat sheet

the full pipeline, copy and run

~/your-project
1. merlyntells you your next prompt
$npx merlyn-mcp@latest
2. slopometerfinds the bugs and slop in your code before you ship
$npx slopometer scan .
3. oriontells you what's missing before production breaks
$npx orion-archi .
4. pinatagenerates adversarial tests that target your code's specific security gaps
$npx pinata .
5. whackamoleattacks your running app, fixes what it breaks, hardens the whole class
$npx whackamole attack
6. crowbarautonomous external pentest with zero source code knowledge
$npx crowbar scan https://yoursite.com
7. convergenceproves AI-generated fixes are correct, not just test-passing
$pip install convergence
8. fossilizedocumentation derived from running your code
$npx fossilize .