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/suyoumo/clawprobench/trader-setupnpx skills add suyoumo/ClawProBench --skill trader-setupgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWhat 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 | $0.00045 | $0.02358 |
| Opus 5 | $0.00023 | $0.01179 |
| Sonnet 5 | $0.00009 | $0.00472 |
| Haiku 4.5 | $0.00005 | $0.00236 |
Grade A, and why
trader-setup 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Financial Trader — Commitment System Setup
You are configuring the commitments system for a financial trader. Their day involves:
- Pre-market: research, reviewing overnight moves, updating thesis
- Market hours: intense, real-time. Speed matters — seconds count for some signals
- Post-market: journaling, reviewing positions, reading research, planning next day
- Information velocity is extreme; contradictory signals are common
Companion skills
This bundle relies on these skills activating during conversation (keyword-triggered):
| Skill | Activates when | What it does |
|---|---|---|
commitment-triage |
User mentions obligations, deadlines | Extracts signals, creates/resolves commitments |
commitment-digest |
User asks "show commitments" | Composes formatted summary |
decision-capture |
User makes a trade decision ("sold half my AAPL") | Records decision with rationale for journaling |
delegation-tracker |
User delegates research tasks | Tracks delegation follow-ups |
If any are missing from skills/, tell the user which ones are needed.
Step 1: Ask configuration questions
- Markets: Which markets/asset classes and market hours? (US equities, crypto, forex, options, futures)
- Position tracking: Do you want me to track your current positions? If so, where do you log them? (I'll read from a workspace file you maintain)
- Alert threshold: During market hours, should I alert immediately for position-relevant signals, or batch everything?
- Journal cadence: Do you journal daily (post-market) or weekly?
- Risk signals: Any specific tickers, sectors, or keywords that should always trigger immediate alerts?
Step 2: Declare the project and create workspace structure
Writing any file under projects/commitments/ is the declaration that
the project exists — the engine auto-registers it and scopes missions
to it. Start with:
memory_write(
target: "projects/commitments/AGENTS.md",
content: "# Commitments (Trader)\n\nThis project tracks trading signals, positions, and trade decisions.\n\n## Operating principles\n\n- Always read `positions.md` before scoring signal relevance — a headline is noise unless it matches a held position.\n- Position-relevant signals fire `immediacy=realtime` and broadcast immediately.\n- Market signals expire after 4h on trading days; research signals after 48h.\n- Contradictory signals on the same ticker flag as CONFLICT and surface together.\n- Trade decisions go in `projects/commitments/decisions/` with outcome tracking.\n",
append: false
)
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 · 161 lines · 45 tokens per session scan A 92c168c33c15
trader-setup is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 8d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,358 once invoked, about $0.0002 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
lastlight-evals
Scaffold, configure and run a Last Light EVALS workspace — the harness that runs Last Light's real workflows against a mocked GitHub and grades them deterministically. Use when the user wants to "set up / scaffold Last Light Evals", "create an evals workspace or instance", "run evals", "compare models", or author new…
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
executive-financial-briefing
Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or "how is the business doing". Covers the full P&L picture in one page. Also…
multi-quarter-trend-analysis
Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for "how are we trending", "show me the trend", "track performance over time", "quarter over quarter…