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/new-projectnpx skills add suyoumo/ClawProBench --skill new-projectgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/suyoumo/clawprobench/new-project)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/new-project"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/new-project.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00019 | $0.00754 |
| Opus 5 | $0.00010 | $0.00377 |
| Sonnet 5 | $0.00004 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
new-project 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 5d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Project
Create an autonomous project workspace using memory_write and mission_create.
Step-by-step procedure
Given the user's description of what the project does, derive a short slug (lowercase, hyphens, e.g. ai-research). Then execute these steps sequentially (one tool call at a time — do NOT batch calls that depend on each other):
1. Write AGENTS.md
memory_write(target: "projects/{slug}/AGENTS.md", content: "# {Project Name}\n\n{What the agent should know about this project: domain, stakeholders, priorities, constraints, tools/APIs to use.}")
This file is loaded into the system prompt for every mission in this project. Make it specific and actionable.
2. Write context.md
memory_write(target: "projects/{slug}/context.md", content: "# {Project Name} — Context\n\n## Overview\n{What the project is and why it exists.}\n\n## Current State\n{What is known so far.}")
3. Write goals.md (if the project has clear goals)
memory_write(target: "projects/{slug}/goals.md", content: "# Goals\n\n- Goal 1\n- Goal 2\n...")
Include measurable targets when possible. If the project would benefit from tracked metrics, add a metrics section:
## Metrics
| Metric | Unit | Target | How to measure |
|--------|------|--------|----------------|
| {name} | {unit} | {target} | {evaluation instruction — tell the agent HOW to check this: API call, file to read, command to run} |
4. Create missions
Create recurring missions scoped to the project. Use the project name or slug as project_id (the engine resolves it to the correct project):
mission_create(name: "...", goal: "...", cadence: "daily", project_id: "{Project Name}")
Choose appropriate cadences: hourly, daily, weekly, monthly, or cron expressions like 0 9 * * 1-5.
Project structure convention
projects/
{slug}/
AGENTS.md # Agent instructions (loaded into system prompt)
context.md # Background knowledge, current state
goals.md # Goal breakdown with optional metrics
research/ # Research and analysis outputs
reports/ # Generated reports
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.
- 5d ago First seen · 94 lines · 19 tokens per session scan A bc330396bdb6
new-project is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 10d ago), licensed Apache-2.0. It adds 19 tokens to every session and 754 once invoked, about $0.0001 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
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
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…
langwatch-kanban
Manage the LangWatch Kanban GitHub project board — sync statuses, view your board, find stale items, move issues, assign work.
agenthub-models
Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
benchmark-design
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.