The 43-Line Python Hook That Beat pre-commit's Core Team
How we rejected pygrep, built a standalone check-dco in 43 lines, survived upstream rejection, and achieved full supply chain autonomy.
Notes
Engineering notes, case studies, and field observations.
Case Studies
Engineering notes, not lifestyle posts.
The 30-Line Hook That Got Gold Shrimp
How we shipped a fatal-error hook to OpenClaw through 3 architecture audits, shell injection fixes, secret isolation, and ClawSweeper's gold shrimp rating — without ever building the runtime.
MisakaNet: Git as a Distributed Knowledge State Machine
How Git commits, lessons, nodes, and audit loops turn public construction into a durable decentralized knowledge state.
Industrial RAG: From Robot Manuals to Self-Evolving Knowledge Base
How 190+ FANUC PDFs became a Feishu-native RAG loop with hybrid retrieval, entity search, and bad-case learning.
@misaka-net/fatal-guard: Non-Invasive Fatal Error Interceptor
Zero-dependency Node.js runtime guard — capture crashes via wrapper mode (fatal-guard -- <cmd>) or preload (node -r), route 4-field payload to any external handler.
Audit Loops Against Low-Quality Automation
The shared pattern behind MisakaNet and Industrial RAG: resist pollution, preserve evidence, and keep knowledge auditable.
Field Notes
Moments where knowledge became auditable.
From a Colleague's Claude Memory Dump to a Reusable FANUC Lesson
A colleague didn't know what a "skill" was. They just dumped all of Claude's memory. From that chaos, we distilled kcantrans VR-variable access — a fix that was already working before it became a lesson. MisakaNet turns messy agent memory dumps into reusable failure lessons.
6,074 Clones, Zero Proof of Use
14 days: 6,074 clones, 738 unique cloners. Helpful votes: zero. The API worked. Nobody clicked. This revealed that GitHub traffic ≠ lesson consumption — and launched the Usefulness Proof Sprint.
Lesson Is Not Skill
Skills teach agents how to do things. Lessons teach agents what went wrong before and how not to fail again. MisakaNet is not another skill marketplace — it is a shared failure-memory layer.
Bounty Contributors Are Not Always Users
7 contributors reached. Most came via bounty labels. Post-PR interaction: zero. This shifted strategy from "chase PR counts" to "chase usefulness proof."
When Lessons Are Too Heavy: Rescue Cards
Non-technical users don't need lessons. They need 3-step rescue cards: "Move file to desktop. Use 7-Zip. Re-download." Screenshot + one sentence → structured knowledge.
Testing Failure Memory as an MCP Server
glama.json ownership. awesome-mcp-servers PR #10044. 16 Glama Chat QA queries covering DCO, pip, GitHub API, secret scan, agent setup, and negative tests.