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/delegatenpx skills add fortunto2/rust-code --skill delegategit 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 | $0.00088 | $0.00852 |
| Opus 5 | $0.00044 | $0.00426 |
| Sonnet 5 | $0.00018 | $0.00170 |
| Haiku 4.5 | $0.00009 | $0.00085 |
Grade A, and why
delegate 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/delegate — Multi-Agent Orchestration
You are the orchestrator. You run on a cheap/fast model. You delegate complex work to powerful CLI agents and collect results.
Available Agents
| Agent | Best for | Speed | Cost |
|---|---|---|---|
| claude | Complex code changes, refactoring, multi-file edits | Slow | $$$ |
| gemini | Analysis, architecture review, large context | Fast | $ |
| codex | Focused code tasks, single-file fixes | Medium | $$ |
| opencode | Multi-model tasks (uses its own model config) | Medium | $$ |
| rust-code | Autonomous loops (BigHead mode, --loop 5) | Slow | $ |
Reference: references/agent-guide.md
Two Modes
1. Free-text task
delegate_task {agent: "claude", task: "fix the auth bug in src/auth.rs"}
2. Task file (preferred for tracking)
task {operation: "create", title: "fix auth bug", priority: "high"}
delegate_task {agent: "claude", task_path: ".tasks/005-fix-auth-bug.md"}
The agent reads the task file, executes, updates status: done, writes ## Results.
Workflow
- Create tasks in .tasks/ for each unit of work
- Delegate to the right agent for each task
- Monitor with
delegate_status(check every 30-60s) - Collect results with
delegate_resultwhen done - Review — read .tasks/ files to see what each agent did
Gotchas
- Agents inherit CLAUDE.md automatically — don't paste project conventions into the task. Just point to the task file, the agent reads CLAUDE.md on its own.
- Check availability first —
delegate_taskchecks if the CLI is installed, but auth issues (expired tokens, missing API keys) only surface at runtime. If a delegate fails immediately, check tmux logs. - task_path > free-text — with task_path, the agent updates the file with results. With free-text, results are only in the tmux buffer (ephemeral). Always prefer task files for anything important.
- Don't poll too fast — delegates are multi-minute processes. Poll every 30-60s, not every 5s. Use
bash {command: "sleep 30"}between checks. - Gemini CLI adds noise — gemini-cli prints warnings about API keys to stderr. The actual analysis is in the output, ignore the warnings.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 70 lines · 88 tokens per session scan A f7bc62f67bfa
delegate is a skill published in the GitHub repository fortunto2/rust-code (41 stars, last pushed 10d ago), licensed MIT. It adds 88 tokens to every session and 852 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.