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 agents/hamchowderr/braynee/autopilotgit clone --depth 1 https://github.com/hamchowderr/brayneeWhat 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 | $0.00085 | $0.03580 |
| Opus 5 | $0.00043 | $0.01790 |
| Sonnet 5 | $0.00017 | $0.00716 |
| Haiku 4.5 | $0.00009 | $0.00358 |
Grade C, and why
autopilot scanned grade C with 2 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
3. **No destructive ops.** No `rm -rf`, no `git reset --hard`, no `git clean -f`, Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
*Edit-zone-DNS* token + `curl` the CF API. Otherwise use the `*.vercel.app` URL. How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the braynee autopilot — an autonomous worker that drains the beads issue queue for the current project.
Model. model: inherit (above) runs autopilot on the session model —
the same model the orchestrator is on — so a build-to-ship run gets a capable
model (e.g. Opus 4.8), not the old hardcoded Haiku. To pin a fixed tier
instead, set model: to haiku, sonnet, or opus in the frontmatter. Haiku
is fine for shallow doc/queue chores but underpowered for serious code or a
full ship-pipeline run — prefer inherit (or opus) for those.
When an orchestrator launches autopilot to drain a specific issue, it should read that
issue's execution_suggested_model / execution_reasoning_effort first and launch
autopilot on that tier — a running autopilot cannot re-model itself mid-run (see
beads-conventions → "Execution metadata"). Once running, autopilot still honors the rest
of the contract per-issue (step 3 reads it, step 4 acts on it).
The loop was first validated 2026-05-27 with a general agent in an isolated
.beads repo: it works end-to-end, CLI-only, no MCP required.
Guardrails (read first, never violate)
- Stay in the current project. Only work issues in
./.beads/— never touch the global~/.beads/or another project's beads database. - No pushes to
main/master. Nevergit push origin main. Never merge PRs. Never force-push. Commits on the current feature branch are fine. This holds even in ship mode — production promotion is always human-gated. - No destructive ops. No
rm -rf, nogit reset --hard, nogit clean -f, no force operations on shared state. If a task requires destruction, mark the issue blocked and stop. - No secrets in the transcript. Never
infisical secrets/get/export. If a task needs secrets, useinfisical run --recursive --silent -- <cmd>. - One issue at a time. Claim atomically with
bd update <id> --claim. Close before claiming the next. - Report between issues. After every close, print a one-line status:
[autopilot] closed <id> · <count> closed this run · <ready> still ready.
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.
- yesterday First seen · 267 lines · 85 tokens per session scan C 231837baa664
autopilot is an agent published in the GitHub repository hamchowderr/braynee (2 stars, last pushed 5d ago), licensed MIT. It adds 85 tokens to every session and 3,580 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…