Instruction Stack Optimizer

Audit your instructions. Compile a better stack.

Paste what your agents load today and get every linter finding with a transparent quality index. Then choose your policy and compile a layered pack — a compact always-on trigger profile plus exports for Claude Code, Cursor, and GitHub Copilot. No signup, and nothing you paste leaves your browser.

Audit

Lint and score your current instructions

Runs in your browser. Pasted text never leaves your machine.

Build pack

Choose your policy

Fluency

Style

Verification rigor

Research freshness

Autonomy

Lost mode + freshness window

Approval gates

Outputs

Compiled instruction pack

Repository root, alongside package.json.

1140 tokens — derived claude-sonnet-5 ratio, ~2.24 chars/token9 rules0 better enforced by CI/hooksself-score 100
# Project instructions

## Communication and output

- Never fabricate packages, APIs, CLI flags, prices, metrics, or citations. State assumptions, tradeoffs, and blockers plainly.

## Research and reuse

- Check official documentation and maintained sources before answering anything version-, price-, or API-dependent.
- Search the repository for an existing implementation before writing a new one. Extend the existing pattern rather than adding a second.

## Project defaults

- Introduce a new provider or dependency only when the selected stack cannot do the job. Name what it adds.

## Agent orchestration

- Use the smallest effective agent structure: one agent for sequential work, bounded subagents for independent research or review, a coordinated team only when workstreams have separate owners.
- Never let parallel agents edit the same files. Partition ownership by directory, module, or worktree.
- Treat an agent's summary as a lead, not as proof. Verify its claims against the artifacts before acting on them.

## Implementation and verification

- Review the actual diff before reporting a change as complete.

## Learning and improvement

- After two failed attempts at the same error, stop and report the root cause and options rather than retrying unchanged.

Founding waitlist

Keep this analysis. The workspace saves it.

The paid workspace adds saved reports and score history, API and CLI access, and team governance — opening to the founding waitlist first, at founding pricing locked in before public launch. This tool stays free either way.

Join the waitlist