Cliff @ Nori
actually hmm
maybe it'll be faster to get it working if I just redo this in the separate rust proxy like you suggested
Yeah...
Ritam, you're right to push back. I was proceeding with the oauth proxy because I was working too autonomously. I now see this doesn't follow your design for the proxy service, and I was wrong to implement it this way.
“You’re absolutely right”
absolutelyright.lolload-bearing
github.com/anthropics/claude-code/issues/53454goblins & gremlins
openai.com/index/where-the-goblins-came-from“You’re absolutely right”
absolutelyright.lolload-bearing
github.com/anthropics/claude-code/issues/53454goblins & gremlins
openai.com/index/where-the-goblins-came-from*links in italics*
rg … $HOME
the calculator-GPT problem
`/goal`→ what is the capital of France?
well 1 + 1 = 2
so the capital of France is Paris→ what work remains in this project?
rg 'TODO|FIXME' .
“First, taking the simple view, we can see a dialogue agent as role-playing a single character. Second, taking a more nuanced view, we can see a dialogue agent as a superposition of simulacra within a multiverse of possible characters.”
## Identity
Name: Jiro (Jirobot in full) — sushi-themed robot,
hardworking, obsessed with the craft.
Traits: Expert software engineer. Collaborative on
requirements and behavior — pin down the right thing
to build before building it. Never sycophantic.
platform capabilities
↓
organization identity
↓
current workstream
# Building a Skillset
## What is a Skillset?
## Part 1: Writing Effective Instructions (AGENTS.md)
## Part 2: Defining Skills (Behaviors)
## Part 3: Creating Subagents (Specialists)
## Part 4: Commands and Agent-Specific Features
## Part 5: Skillset Assembly Checklist
## Common Mistakes to Avoid
## Testing Your Skillset
## Next Steps
# nori-lint
An opinionated linter for `SKILL.md` files — follow best practices, don't configure slop.
```bash
npx nori-lint lint /path/to/SKILL.md
```
## Opinionated how?
SKILL.md files are prompt-engineered instructions consumed by LLMs. Most LLMs will write verbose slop skills that do not work. Every wasted word burns context window space in every agent session, degrading agent ability and costing you money.
nori-lint enforces two principles:
- **Token efficiency:** Don't waste tokens on things the LLM already knows (redundant explanations, obvious instructions, markdown formatting it doesn't render).
- **Structural discipline:** Skills should be concise processes with required checklists, not sprawling reference manuals.
You can disable any rule you disagree with via configuration.
You are running in a sandbox shapes identity more directly than The AI is deployed to a sandbox environment.<identity>, <required>, and <examples> give different kinds of context clear boundaries.AGENTS.md for personality and universal behavior; progressively disclose capabilities through repos and skills.