neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
Agentic-SDLC audit tool built entirely through the pipeline it documents: plan, agent build, adversarial AI review, CI gate, human-authorized merge. Deterministic scored reports on AI-agent developmen
Developer toolsJavaScript · TypeScriptGitHub @ryanportfolioOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Agentic-SDLC audit tool built entirely through the pipeline it documents: plan, agent build, adversarial AI review, CI gate, human-authorized merge. Deterministic scored reports on AI-agent development discipline.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
The model that wrote the code never grades it.
Both passes are skills I wrote: handoff audit and /codex-review. How I score all of it.
Those skills ship with Harness Firmware, the self-syncing template I start every repo from. The part that does the work is a reference library the agent writes back into: every gotcha that bites once gets recorded as a pitfall, and the next session reads it before touching that area. Knowledge accumulates in the repo instead of evaporating when a session ends.
fullbuild.ai carries this work with case notes and live prototypes. Background is on my about page.Read the full README ↗The model that wrote the code never grades it.
Both passes are skills I wrote: handoff audit and /codex-review. How I score all of it.
Those skills ship with Harness Firmware, the self-syncing template I start every repo from. The part that does the work is a reference library the agent writes back into: every gotcha that bites once gets recorded as a pitfall, and the next session reads it before touching that area. Knowledge accumulates in the repo instead of evaporating when a session ends.
fullbuild.ai carries this work with case notes and live prototypes. Background is on my about page.