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/statusgit clone --depth 1 https://github.com/Bitmia-ai/RedEyeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/bitmia-ai/redeye/status)<a href="https://agentmods.dev/commands/bitmia-ai/redeye/status"><img src="https://agentmods.dev/badge/commands/bitmia-ai/redeye/status.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00013 | $0.00493 |
| Opus 5 | $0.00006 | $0.00246 |
| Sonnet 5 | $0.00003 | $0.00099 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
status 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 3d 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.
What it actually says
You are presenting the CEO's status dashboard. Follow these steps:
Step 1: Read State Files
Read these files from the project root:
.redeye/state.json— for health, confidence, iteration count, phase, blocked items.redeye/status.md— for the full dashboard.redeye/inbox.md— for pending questions and credential requests
Step 2: Present Summary
Show the user a concise status summary in this order:
Health at a glance:
- Team confidence: {HIGH/MEDIUM/LOW} from state
- Dev environment: {healthy/unhealthy}
- Current iteration: {n}, phase: {phase}
- Iterations since last deploy: {n}
What happened (from .redeye/status.md "Just Completed" section):
- Recent completions from last 3 iterations
What needs your attention (from .redeye/inbox.md):
- Count of open questions and credential requests
- List the highest-priority items with their defaults
What's coming next (from .redeye/status.md "Up Next"):
- Current work in progress
- Next planned items
Step 3: Interactive Follow-up
After presenting the summary, offer the user choices via AskUserQuestion:
- "Answer pending questions" — if there are open questions, walk through each using AskUserQuestion with the options from .redeye/inbox.md
- "Add a task" — ask for a title and description, then create it via
scripts/create-task.sh - "Steer the team" — ask for a directive, then write it via
scripts/add-steering.sh - "Done" — exit
If the user chooses to answer questions, walk through each open question in .redeye/inbox.md one at a time using AskUserQuestion, presenting the options listed in the question. Write each CEO answer via scripts/answer-question.sh; do not edit .redeye/inbox.md directly.
If the user chooses to add a task, call scripts/create-task.sh --section ceo; do not hand-author a ### T<NNN>: block.
If there are pending credential requests, mention them and explain that the CEO should add secret values to .env.test manually.
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.
- 3d ago First seen · 48 lines · 13 tokens per session scan A 8146f06ed464
status is a command published in the GitHub repository Bitmia-ai/RedEye (6 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 493 once invoked, about $0.0001 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-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-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-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.