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/idea-parkingnpx skills add suyoumo/ClawProBench --skill idea-parkinggit 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/idea-parking)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/idea-parking"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/idea-parking.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 5.1 | $0.00023 | $0.00771 |
| Opus 5 | $0.00012 | $0.00385 |
| Sonnet 5 | $0.00005 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
idea-parking 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 6d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Parking
Manage ideas that are interesting but not yet actionable. Parked ideas live in projects/commitments/parked-ideas/ and are periodically resurfaced by the digest.
Parking an idea
User says: "park this idea: do a comparison video of AWS vs GCP" or "save for later: investigate Rust WASM performance."
This skill is only successful if the parked idea is actually persisted. Do not just acknowledge or summarize an idea.
Execution order is mandatory:
- Call
memory_writeforprojects/commitments/parked-ideas/<slug>.md - Only then confirm what was parked
Never say an idea was "parked", "saved for later", or "resurfaced later"
unless the corresponding memory_write succeeded.
Action:
- Write to
projects/commitments/parked-ideas/<slug>.md:
---
type: parked-idea
parked_at: <today YYYY-MM-DD>
source: conversation
relevance: <high|medium|low — infer from user's enthusiasm>
tags: [<relevant tags>]
---
# <Idea title>
<Description and why it is interesting.>
## Activation trigger
<What would make this worth pursuing — a condition, event, or timeframe.>
- Confirm only after the write succeeds: "Parked: . I'll resurface it when the time seems right."
Listing parked ideas
User says: "show parked ideas" or "what's on the backburner?"
Action:
memory_tree("projects/commitments/parked-ideas/", depth=1)— list all files (skip README.md)memory_readeach to get title and relevance- Display a brief list:
Parked ideas: - **<title>** (parked <date>, relevance: <level>) - **<title>** (parked <date>, relevance: <level>)
Promoting an idea
User says: "activate the comparison video idea" or "let's do the WASM performance investigation."
Action:
- Find the matching parked idea
- Create a commitment in
projects/commitments/open/based on the idea content - Overwrite the parked idea file with empty content
- Confirm: "Promoted to active commitment: ."
Dismissing an idea
User says: "dismiss the comparison video idea" or "drop that parked idea."
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.
- 6d ago First seen · 99 lines · 23 tokens per session scan A d17108bed7ff
idea-parking is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 11d ago), licensed Apache-2.0. It adds 23 tokens to every session and 771 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.
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…
remote-claude-code
Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…
penguin-harness-dev
Use when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing release screenshots; deciding what to do about data already on…
benchmark-design
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.
unified-llm-api
Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.