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 skills/fortunto2/rust-code/bigheadnpx skills add fortunto2/rust-code --skill bigheadgit clone --depth 1 https://github.com/fortunto2/rust-codeWhat 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 | $0.00074 | $0.00468 |
| Opus 5 | $0.00037 | $0.00234 |
| Sonnet 5 | $0.00015 | $0.00094 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
bighead 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
BigHead — Autonomous Task Loop
Named after Nelson Bighetti from Silicon Valley. You run autonomously until the task is done. The human may be asleep.
Core Loop
Each iteration: assess → plan → execute → test → commit → continue or stop.
Use .tasks/ for tracking progress across iterations. Read Makefile for available commands.
Signals
- Task complete → include
<solo:done/>in finish summary - Needs retry → include
<solo:redo/> - Control file:
echo stop > .rust-code/loop-control
Gotchas
- Commit before you forget — if you accumulate a large diff and the next step fails, you lose everything. Commit after every meaningful change, even if incomplete.
- Pre-commit hooks will bite you —
make checkruns tests + clippy + fmt. If you skip it and commit directly, the hook will reject. Alwaysmake fmtbefore committing. - Loop detector triggers on repetition — if you call the same tool 5+ times with similar args, the loop detector aborts. Vary your approach — don't retry the same failing command.
- Don't ask the human — you are autonomous. If stuck, try a different approach, read more code, check git log. Never call
ask_user. - Test command varies by project — don't assume
cargo test. ReadMakefileorpackage.jsonfirst.make helpshows all targets.
When to Stop
Include <solo:done/> when: all tasks done + tests pass + code committed + result verified.
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 · 35 lines · 74 tokens per session scan A 18a2183c6917
bighead is a skill published in the GitHub repository fortunto2/rust-code (41 stars, last pushed 10d ago), licensed MIT. It adds 74 tokens to every session and 468 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
test-repo
Use this skill to test strategy changes against a fresh test repository. Invoke when the user asks to "test against a test repo", "validate the changes", or wants to verify session hooks, commits, and rewind functionality work correctly.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
model-update
新增或更新 CCX 项目中的模型注册技能。适用于 Claude 与非 Claude 模型，覆盖能力表、路由白名单、基准映射、代码生成与验证。.
conductor-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.
bionic-decision-engine
Unified mathematical arbitrator for all resource allocation decisions — money, time, energy, relationships. Absorbs 46 decision protocols + 24 strategy protocols into one dense engine.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.