apply-consequence-clarity

apply-consequence-clarity is a skill for Claude Code from jeffreytse/grimoire-core. It costs 49 tokens per session (2,921 once invoked), scanned A, original, MIT.

A framework for designing rewards and penalties so people can understand them, expect them to happen, and see them applied quickly and proportionately. It connects behavioral feedback with the timing and consistency of consequences.

In plain words
What is it for?
Use it for performance management, compliance rules, software quality processes, or habit-building systems. It helps define which behavior leads to which consequence and when it should follow.
Why use it?
Unclear, delayed, or unreliable consequences rarely change behavior. This helps make feedback systems more predictable and effective.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grimoire-business plugin — 145 skills shipped together

Good fit Use it for performance management, compliance rules, software quality processes, or habit-building systems. It helps define which behavior leads to which consequence and when it should follow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/apply-consequence-clarity
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 jeffreytse/grimoire-core --skill apply-consequence-clarity
Clone the repo
git clone --depth 1 https://github.com/jeffreytse/grimoire-core

Made for: Claude Code.

Or install grimoire-business, the plugin that ships this one along with the rest of its 145 skills.

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 apply-consequence-clarity

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-consequence-clarity/github.svg)](https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-consequence-clarity)
Your own site
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-consequence-clarity"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-consequence-clarity/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 apply-consequence-clarity

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-consequence-clarity"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-consequence-clarity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,921 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 $0.00049 $0.02921
Opus 5 $0.00024 $0.01460
Sonnet 5 $0.00010 $0.00584
Haiku 4.5 $0.00005 $0.00292

Measured 8d ago against content hash 99d440e12997, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

apply-consequence-clarity 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.

skills/business/strategy/skills/apply-consequence-clarity/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply Consequence Clarity

Design consequences to be clear, certain, and swift — because certainty and timing determine behavior modification more than magnitude, and a small immediate consequence changes behavior more reliably than a large delayed one.

Why This Is Best Practice

Shang Yang's 赏刑篇 (~4th century BC) articulates four required properties of effective rewards and punishments: 明 (clear — people know exactly which behavior leads to which consequence), 必 (certain — consequence reliably follows the behavior), 速 (swift — minimal delay between behavior and consequence), and 平 (proportionate — severity matches the offense). His argument: a legal system with low certainty of enforcement is worse than no system — it teaches people that violations are low-risk. The consequence properties matter more than their magnitude. This principle was the operating foundation of Shang Yang's legal reforms in Qin, which transformed Qin from a weak peripheral state into the power that ultimately unified China.

B.F. Skinner — operant conditioning: The foundational finding in behavioral psychology: reinforcement timing and consistency determine behavior change far more than reward magnitude. A lever-press rewarded immediately produces rapid conditioning; the same reward delivered 30 seconds later produces no conditioning. Fixed-ratio schedules (certain reward every N responses) produce sustained behavior; variable-ratio schedules (uncertain) produce higher frequency but lower stability. This research is the basis of behavioral therapy, organizational behavior management, and behavioral economics globally.

Daniel Kahneman & Amos Tversky — Prospect Theory (1979, Nobel 2002): People discount future consequences exponentially with delay (temporal discounting). A $100 consequence tomorrow is psychologically valued much higher than a $100 consequence in six months, even though the amounts are identical. Consequence timing determines psychological impact, not just nominal value.

Read the full file on GitHub · 83 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. 8d ago First seen · 83 lines · 49 tokens per session scan A 99d440e12997

Subscribe to this mod's changes

apply-consequence-clarity is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 23d ago), licensed MIT. It adds 49 tokens to every session and 2,921 once invoked, about $0.0002 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.