stopping-criteria

stopping-criteria is a skill for Claude Code, Codex from openscientist-io/openscientist. It costs 15 tokens per session (1,636 once invoked), scanned A, original, Apache-2.0.

A decision guide for knowing when a research investigation has gathered enough evidence to write its final report.

In plain words
What is it for?
Use it when deciding whether to continue investigating, synthesize findings, or stop because the evidence supports a coherent explanation, the budget is exhausted, or the data is fundamentally flawed.
Why use it?
It prevents wasted work after the iteration or cost limit is reached and identifies failures that make further analysis unreliable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when deciding whether to continue investigating, synthesize findings, or stop because the evidence supports a coherent explanation, the budget is exhausted, or the data is fundamentally flawed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openscientist-io/openscientist/stopping-criteria
Install

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.

Any agent
npx skills add openscientist-io/openscientist --skill stopping-criteria
Clone the repo
git clone --depth 1 https://github.com/openscientist-io/openscientist

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for stopping-criteria

README.md
[![agentmods](https://agentmods.dev/badge/skills/openscientist-io/openscientist/stopping-criteria/github.svg)](https://agentmods.dev/skills/openscientist-io/openscientist/stopping-criteria)
Your own site
<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.

agentmods 80×15 button for stopping-criteria

Your own site · 80×15
<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>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,636 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash a46fc3b45428, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

skills/workflow/stopping-criteria/SKILL.md · 290 lines

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

Read the full file on GitHub · 290 lines

Changes

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.

  1. 10d ago First seen · 290 lines · 15 tokens per session scan A a46fc3b45428

Subscribe to this mod's changes

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.