falsifiability-test-pattern

falsifiability-test-pattern is a skill for Claude Code, Codex from fabioc-aloha/Alex_Skill_Mall. It costs 18 tokens per session (548 once invoked), scanned A, original, MIT.

A planning pattern that gives every proposed change a measurable way to prove whether it worked or failed.

In plain words
What is it for?
Use it to define metrics, baselines, targets, evaluation periods, and fallback decisions for features or technical improvements.
Why use it?
Vague goals such as “make it faster” can drift without evidence, targets, or a clear decision about what to do next.

Skill for Claude CodeCodex

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

Good fit Use it to define metrics, baselines, targets, evaluation periods, and fallback decisions for features or technical improvements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fabioc-aloha/alex_skill_mall/falsifiability-test-pattern
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 fabioc-aloha/Alex_Skill_Mall --skill falsifiability-test-pattern
Clone the repo
git clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_Mall

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 falsifiability-test-pattern

README.md
[![agentmods](https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/falsifiability-test-pattern/github.svg)](https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/falsifiability-test-pattern)
Your own site
<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/falsifiability-test-pattern"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/falsifiability-test-pattern/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 falsifiability-test-pattern

Your own site · 80×15
<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/falsifiability-test-pattern"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/falsifiability-test-pattern.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 548 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.
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 $0.00018 $0.00548
Opus 5 $0.00009 $0.00274
Sonnet 5 $0.00004 $0.00110
Haiku 4.5 $0.00002 $0.00055

Measured 8d ago against content hash 45050e4e574c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

falsifiability-test-pattern 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 8d 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.

plugins/code-quality/falsifiability-test-pattern/skills/falsifiability-test-pattern/SKILL.md · 90 lines

What it actually says

Falsifiability Test Pattern

The Problem

Plans without measurable success criteria drift into wishful thinking:

  • "Improve performance" — how much? by when?
  • "Better user experience" — measured how?
  • "Reduce tech debt" — which debt? how will we know?

The Solution

Every deferred or speculative work item declares a measurable rule for success/failure.

## Feature: Caching Layer

**Hypothesis**: Adding Redis caching will reduce API latency by 50%.

**Falsifiability Test**: 
- Measure: p95 latency for /api/users endpoint
- Baseline: 450ms (measured 2026-04-20)
- Target: <225ms
- Window: 30 days post-deployment
- Decision rule: If p95 > 300ms after 30 days, revert and investigate

**Evidence collection**: Datadog dashboard, weekly snapshots

Template

## [Feature/Change Name]

**Hypothesis**: [What you believe will happen]

**Falsifiability Test**:
- Measure: [Specific metric]
- Baseline: [Current value with date]
- Target: [Success threshold]
- Window: [Time to evaluate]
- Decision rule: [What to do if fails]

**Evidence collection**: [How you'll gather data]

Good vs Bad Tests

Bad Good
"Will be faster" "p95 latency < 200ms within 14 days"
"Users will like it" "NPS > 40 after 500 responses"
"Reduces bugs" "Bug reports for module X < 2/month"
"More maintainable" "Time to implement similar feature < 2 days"

Decision Rules

| Outcome | Action |
|---------|--------|
| Target met | Keep, document win |
| Partial (80%+) | Keep, note limitation |
| Missed | Revert or iterate |
| Can't measure | Fix instrumentation first |

Verification

  1. Every plan item has a falsifiability test
  2. Tests have specific numbers and dates
  3. Decision rules exist before implementation
  4. Results are recorded

When to Apply

  • Feature planning
  • Architecture decisions
  • Process changes
  • Any speculative investment

Tags

quality planning metrics decision-making

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. 8d ago First seen · 90 lines · 18 tokens per session scan A 45050e4e574c

Subscribe to this mod's changes

falsifiability-test-pattern is a skill published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 548 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 2026-09-03.

Related

Other skills, from other repositories

apply-cross-functional-leadership

Use when a manager needs to lead a project or initiative that depends on team members or stakeholders they do not formally manage — to build voluntary cooperation, alignment, and momentum across organizational boundaries through influence rather than authority.

jeffreytse/grimoire-core · 49 tokens

build-psychological-safety

Use when a team leader wants to assess and improve the degree to which team members feel safe to speak up, admit mistakes, ask questions, and disagree — because psychological safety is the strongest predictor of team learning and high performance.

jeffreytse/grimoire-core · 52 tokens

run-performance-improvement-plan

Use when a direct report has a documented pattern of performance falling below role expectations — after informal feedback has not produced sustained change — to create a structured, time-bound plan with clear success criteria before making a continuation decision.

jeffreytse/grimoire-core · 49 tokens

run-underperformance-conversation

Use when a manager first observes that a direct report's performance is declining or falling below expectations — to have an early, direct, non-punitive conversation that names the gap and opens a path to correction before the situation requires formal process.

jeffreytse/grimoire-core · 54 tokens

apply-change-leadership

Use when a manager's team is experiencing a significant organizational change — restructuring, strategy shift, leadership change, layoffs, or major process transition — and needs leadership that maintains team stability, preserves trust, and converts uncertainty into direction.

jeffreytse/grimoire-core · 51 tokens

apply-distributed-team-practices

Use when managing a team where members work in different locations, time zones, or on hybrid schedules — to adapt management practices so remote members have equal access to information, relationships, and advancement opportunities as in-office members.

jeffreytse/grimoire-core · 51 tokens