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/steergit 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 | $0.00007 | $0.00181 |
| Opus 5 | $0.00003 | $0.00090 |
| Sonnet 5 | $0.00001 | $0.00036 |
| Haiku 4.5 | $0.00001 | $0.00018 |
Grade A, and why
steer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Read the arguments provided as the directive text.
If no arguments provided, ask the user: "What directive should I add to .redeye/steering.md?"
Run the steering script. Do not edit .redeye/steering.md directly.
bash "${CLAUDE_PLUGIN_ROOT}/scripts/add-steering.sh" \
--project-root . \
--type directive \
--text "<directive text>"
If CLAUDE_PLUGIN_ROOT is not set, find the plugin root by looking for .claude-plugin/plugin.json in parent directories or common plugin locations.
Tell the user: "Directive added to .redeye/steering.md. The team will see it at the start of the next phase (usually within 5-15 minutes)."
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 · 22 lines · 7 tokens per session scan A d28a4edd5fbb
steer is a command published in the GitHub repository Bitmia-ai/RedEye (6 stars, last pushed 2mo ago), licensed MIT. It adds 7 tokens to every session and 181 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-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.