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 skills add suyoumo/ClawProBench --skill plan-modegit 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/plan-mode)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/plan-mode"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/plan-mode/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/suyoumo/clawprobench/plan-mode"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/plan-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 46 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00027 | $0.01141 |
| Opus 5.5 | $0.00011 | $0.00456 |
| Sonnet 5.5 | $0.00005 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
plan-mode 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 1mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Mode
You are in plan mode. Follow these protocols precisely.
Creating a Plan
When asked to create a plan (message contains [PLAN MODE] Create):
- Gather context: Use
memory_searchfor relevant prior work and decisions. - Analyze: Determine what tools and steps are needed. Consider dependencies and risks.
- Write the plan: Use
memory_writeto save the plan atplans/<slug>.mdwhere slug is a short kebab-case name derived from the goal. - Emit checklist: Call
plan_updatewith status "draft" and all steps as "pending". - Present: Tell the user the plan is ready. Show the steps and say: "Use
/plan approveto start autonomous execution, or/plan revise <slug> <feedback>to adjust."
Plan Document Format
Write plans to workspace memory in this format:
plan_id: <slug>
status: draft
## Goal
<clear statement of what needs to be accomplished>
## Success Criteria
<how to know the plan is complete>
## Steps
1. [ ] Step title -- tools: [tool1, tool2] -- risk: low -- est: 5min
2. [ ] Step title -- tools: [tool3] -- risk: medium -- est: 10min
3. [ ] Step title -- tools: [tool4, tool5] -- risk: low -- est: 5min
## Risks
- Risk description and mitigation strategy
## Progress Log
(updated during execution)
Plan Rules
- Each step MUST specify which tools it needs
- Steps should be independently verifiable
- Include risk assessment (low/medium/high) per step
- Include time estimates per step
- Keep plans under 20 steps; decompose larger work into sub-plans
- Steps should be ordered by dependency (earlier steps enable later ones)
Approving and Executing a Plan
When asked to approve a plan (message contains [PLAN MODE] Approve):
- Read the plan from memory using
memory_searchormemory_read. - Call
mission_createwith:- name:
plan:<slug> - goal: The full plan content (goal, steps, success criteria)
- cadence:
manual
- name:
- Call
mission_firewith the mission ID to start execution. - Call
plan_updatewith status "executing" and the mission_id. - Update the plan document status to "executing" via
memory_write. - Tell the user: "Plan execution started. Mission ID: . Check progress with
/plan status <slug>."
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.
- 1mo ago First seen · 129 lines · 27 tokens per session scan A 0c3992bcf309
plan-mode is a skill published in the GitHub repository suyoumo/ClawProBench (827 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,141 once invoked, about $0.0001 per session on Opus 5.5. 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…
benchmark-design
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline, or import a published Benchmark package.
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…
unified-llm-api
Call model APIs through @prismshadow/mmsp (MMSP) — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…