Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/bitmia-ai/redeye/initgit clone --depth 1 https://github.com/Bitmia-ai/RedEyeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00006 | $0.01321 |
| Opus 5 | $0.00003 | $0.00660 |
| Sonnet 5 | $0.00001 | $0.00264 |
| Haiku 4.5 | $0.00001 | $0.00132 |
Grade A, and why
init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize RedEye
Set up the autonomous dev team framework in this project.
Pre-flight Check
Before anything else, check if .redeye/state.json exists in the current directory:
- If it exists: tell the user "This project is already initialized with RedEye. Use
/redeye:startto resume, or run/redeye:init --forceto reinitialize (this will overwrite all control files and reset state)." Then STOP — do not proceed. - If
--forceis passed alongside an existing project: warn the user that all control files will be overwritten and state will be reset. Ask for confirmation via AskUserQuestion before proceeding.
Detect Mode
Check if arguments include --full:
- If
--full: run Full Setup (all steps below) - Otherwise: run Quick Start (steps 1-5 only)
Quick Start (~2 minutes)
Step 1: Project Name
Ask via AskUserQuestion:
- Question: "What's the project name?"
- Default: basename of the current working directory
Step 2: Product Vision
Ask via AskUserQuestion:
- Question: "Describe your product vision in one sentence"
- This becomes the ## Vision section in .redeye/config.md
Step 3: First Task
Ask via AskUserQuestion:
- Question: "What should we build first?"
- This becomes the first CEO Request in .redeye/tasks.md (T001)
Step 4: Deploy Command
Ask via AskUserQuestion:
- Question: "What's your deploy command?"
- Options: common patterns like
./scripts/deploy.sh deploy,npm run deploy,git push heroku main, custom - Default: "echo 'No deploy command configured'"
Step 5: Scaffold
CRITICAL: You MUST run the init-project.sh script. Do NOT create control files manually. The script creates state.json, sets up gitignore entries, installs the pre-commit hook, and makes the initial commit. Without it, /redeye:start will not work.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 124 lines · 6 tokens per session scan A cacb6c4b403c
init is a command published in the GitHub repository Bitmia-ai/RedEye (6 stars, last pushed 2mo ago), licensed MIT. It adds 6 tokens to every session and 1,321 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
dark-factory-synthesize-verdict
Final arbiter for Dark Factory PR validation. Aggregates behavioral, security, code review, and static check results into an approve/requestchanges/reject verdict.
dark-factory-validate
Run Dark Factory validation — Python backend (ruff + mypy + pytest) + React frontend (tsc + biome + vitest).
dark-factory-behavioral-e2e
Holdout-pattern E2E validator. Drives agent-browser against the running DynaChat app to verify that the PR's user-facing behavior actually matches what the linked issue asked for.
dark-factory-fix-issue
Implement a fix from investigation artifact for the Dark Factory — code changes, Python + Bun deps, light validation, commit (no PR).
dark-factory-synthesize-verdict-p2
Pass-2 variant of dark-factory-synthesize-verdict. Reads -p2 node outputs (post-fix). Aggregates behavioral, security, code review, and static check results into an approve/requestchanges/reject verdict.
dark-factory-fix-pr-issues
Apply targeted fixes to a PR based on validation feedback from dark-factory-validate-pr pass 1. Reads only the structured issuestofix list — never the original implementation plan.