Borrowing it
Nothing to install: this file belongs to fabioc-aloha/Alex_Skill_Mall. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fabioc-aloha/Alex_Skill_Mall/main/.github/instructions/falsifiability-deadlines.instructions.mdgit clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_MallWrote 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/instructions/fabioc-aloha/alex_skill_mall/falsifiability-deadlines)<a href="https://agentmods.dev/instructions/fabioc-aloha/alex_skill_mall/falsifiability-deadlines"><img src="https://agentmods.dev/badge/instructions/fabioc-aloha/alex_skill_mall/falsifiability-deadlines/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/instructions/fabioc-aloha/alex_skill_mall/falsifiability-deadlines"><img src="https://agentmods.dev/badge/instructions/fabioc-aloha/alex_skill_mall/falsifiability-deadlines.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01167 | $0.01167 |
| Opus 5 | $0.00583 | $0.00583 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
Alex_Skill_Mall falsifiability-deadlines.instructions.md 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 9d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Falsifiability deadlines
Every brain artefact must commit to a specific falsification deadline at creation time, not "after N passes" or "when conditions warrant." Vague kill-criteria let an artefact's falsification be indefinitely deferred while the artefact accumulates token cost and authority in the brain.
The rule
Every artefact's ## Falsifiability or ## Would Revise If section must include at least one of:
- Date-based deadline: "If not met by , sunset this artefact."
- Event-based trigger: "If occurs without the artefact firing as designed, sunset this artefact."
- Count-based with time bound: "If after N AND by , hasn't held, sunset this artefact." (N-only is not sufficient.)
The deadline must be specific enough that "did it happen?" is answerable by a third party reading the brain six months later.
What this prevents
| Failure mode | Without deadline | With deadline |
|---|---|---|
| Skill never invoked, no one notices | Accumulates in brain indefinitely | At deadline, gets evaluated; if unused, sunsets |
| Skill invoked but never produces signal | No clock running | Deadline forces explicit "did it produce signal?" check |
| Author hopes future evidence will materialise | Hope continues indefinitely | Hope expires on date D |
| Reader can't tell if artefact is alive or stalled | No sunset clock | Sunset triggers on a known schedule |
What this doesn't require
- Aggressive deadlines. "60 days from creation" is fine if that's a realistic test window. The point is commitment, not haste.
- Single-point falsification. An artefact can have multiple falsification paths (date + event, or multiple events).
- Retroactive application to all existing artefacts. Files created before 2026-05-24 are unaffected until separately swept. The bulk sweep is a follow-up to this proposal.
Template
Add to the artefact's ## Falsifiability (skills) or ## Would Revise If (instructions) section:
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.
- 9d ago First seen · 81 lines · 1,167 tokens per session scan A 20042ce89f67
Alex_Skill_Mall falsifiability-deadlines.instructions.md is an instructions file published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed yesterday), licensed MIT. It adds 1,167 tokens to every session, about $0.0058 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.