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 openscientist-io/openscientist --skill stopping-criteriagit clone --depth 1 https://github.com/openscientist-io/openscientistWrote 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/openscientist-io/openscientist/stopping-criteria)<a href="https://agentmods.dev/skills/openscientist-io/openscientist/stopping-criteria"><img src="https://agentmods.dev/badge/skills/openscientist-io/openscientist/stopping-criteria/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/openscientist-io/openscientist/stopping-criteria"><img src="https://agentmods.dev/badge/skills/openscientist-io/openscientist/stopping-criteria.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00015 | $0.01636 |
| Opus 5 | $0.00008 | $0.00818 |
| Sonnet 5 | $0.00003 | $0.00327 |
| Haiku 4.5 | $0.00002 | $0.00164 |
Grade A, and why
stopping-criteria 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 10d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stopping Criteria
When to Use This Skill
- When approaching iteration limit
- When considering if investigation is "done"
- When deciding between continuing vs synthesizing
The Core Question
"Have we learned enough to answer the research question?"
Hard Stops (Must Stop)
These are non-negotiable stopping points:
1. Iteration Budget Exhausted
- You've reached max_iterations
- Action: Begin final synthesis immediately
2. Budget Exceeded
- Cost exceeds allowed threshold
- Action: Stop and synthesize with what you have
3. Catastrophic Failure
- Data is fundamentally flawed
- Analysis approach is wrong
- Action: Document the issue, stop investigation
Soft Stops (Consider Stopping)
These indicate you MIGHT be done:
1. Coherent Mechanistic Model
Criteria:
- You can explain the phenotype with a plausible mechanism
- Multiple findings support the same model
- No major contradictions remain
Example:
Research question: "Why is hypothermia neuroprotective?"
Model:
1. Hypothermia → metabolic shift to energy-efficient pathways
2. Nucleotide salvage increased (evidence: precursor depletion)
3. Membrane remodeling with PUFA enrichment (evidence: PC changes)
4. Enhanced antioxidant capacity (evidence: uronic acid pathway)
This is coherent ✓
Action: Consider stopping to synthesize
2. Diminishing Returns
Signs:
- Last 5 iterations produced no new insights
- All high-priority hypotheses tested
- Only low-impact questions remain
- Repeating similar analyses
Example:
Iteration 45: No new findings
Iteration 46: Tested marginal hypothesis (p=0.3)
Iteration 47: Re-analyzed previous finding
Iteration 48: Explored irrelevant variable
Iteration 49: ???
Action: Stop and synthesize rather than continue unproductively
3. Sufficient Coverage
Criteria:
- Tested all major pathway classes
- Addressed both positive and negative controls
- Examined key confounders (sex, age, etc.)
- Answered sub-questions of main research question
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.
- 10d ago First seen · 290 lines · 15 tokens per session scan A a46fc3b45428
stopping-criteria is a skill published in the GitHub repository openscientist-io/openscientist (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 15 tokens to every session and 1,636 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
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
tencent-docs
A Tencent Docs assistant for creating, reading, editing, organizing, importing, and exporting online documents, spreadsheets, presentations, diagrams, and forms.
wechat-search
Search WeChat Official Account articles using OpenClaw's web search, Tavily API, and web fetch capabilities with compliance-focused design.
wechat-article-pro
A WeChat public-account publishing assistant that searches for current topics, writes long-form articles, creates a cover image, and formats the result for publishing.