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 deciqAI/knowledge-skills --skill peak-end-rulegit clone --depth 1 https://github.com/deciqAI/knowledge-skillsWrote 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/deciqai/knowledge-skills/peak-end-rule)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/peak-end-rule"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/peak-end-rule/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/deciqai/knowledge-skills/peak-end-rule"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/peak-end-rule.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 | $0.00122 | $0.02127 |
| Opus 5 | $0.00061 | $0.01064 |
| Sonnet 5 | $0.00024 | $0.00425 |
| Haiku 4.5 | $0.00012 | $0.00213 |
Grade A, and why
peak-end-rule 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peak-End Rule
Overview
People remember experiences not by averaging all moments but by sampling two: the peak (highest emotional intensity) and the end. Everything in between — including duration — is largely discarded. This is the peak-end rule, from Kahneman et al. (1993) and Redelmeier & Kahneman (1996).
Global evaluation ≈ (peak intensity + end intensity) / 2. Experience design is not an averaging problem — it is a peak-and-ending problem.
Neighbor skills: Use after aarrr-pirate-metrics to place the peak in the right lifecycle stage; use anchoring to set expectation baselines peaks must exceed; pair with nudge-theory to smooth the path to the peak and ending; use probabilistic-thinking before designing peaks to estimate expected effect size.
When to Use
Apply when:
- Designing or auditing a multi-stage experience with a clear start and end (onboarding, service encounter, event, medical visit)
- NPS or satisfaction scores are lower than expected given average perceived quality
- A competitor with similar objective quality consistently earns higher recommendation rates
- Allocating limited resources across experience stages and need to know where to concentrate
When NOT to use: purely instantaneous interactions with no duration; real-time performance optimization (not retrospective rating); welfare/health assessments where experienced utility — not memory — is the correct measure; one-time required events with no competitive alternative.
Coaching Novices (Adaptive Front Door)
- Engine mode: concrete journey to audit → run The Process directly.
- Coach mode: unfamiliar or no concrete case → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- What-it-is: people remember by their strongest moment and how it ended — the middle barely matters.
- Check fit: instantaneous interaction or real-time utility goal → redirect.
- Elicit their real journey — get actual stages and where emotion rises and falls.
[WAIT — do not advance until user responds]
- Walk through emotion map; identify current peak and ending; ask what "better" looks like for those two points only.
[WAIT — do not advance until user responds]
- Name the one change most likely to move NPS/return rate and the metric to confirm it.
[WAIT — do not advance until user responds]
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 120 lines · 122 tokens per session scan A 5ba03b85f2a9
peak-end-rule is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 122 tokens to every session and 2,127 once invoked, about $0.0006 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.
Other skills, from other repositories
ui-ux-pro-max
Builds an end-to-end UI system for a product — design tokens (color scale, type scale, spacing, radii, shadows), a component inventory covering every interaction state, a layout grid, and WCAG contrast checks — emitted as CSS variables plus a component spec doc. Use when the user says "set up a design system", "create…
taste
Delivers a ruthless, structured critique of any screen, mockup or site — scores hierarchy, spacing rhythm, contrast, typography pairing and color discipline /10 with evidence, detects clichés (purple gradients, glassmorphism-by-default, emoji soup, cookie-cutter heroes), and ranks the top 5 highest-leverage fixes with…
web-artifacts
Turns any idea into a live single-file HTML prototype in minutes — inline CSS/JS, CDN-only dependencies (cdnjs), mobile-first, seeded with believable fake data, interactive states wired — ready to open in a browser or paste as a Claude artifact. Use when the user says "prototype this", "show me a working demo", "make…
lightweight-design
A lightweight design-planning skill for resolving high-risk decisions before a coding task begins. It records the facts, affected areas, chosen decisions, and how those decisions map to requirements and acceptance checks.
design-preview
A method for turning an existing or proposed interface into a self-contained HTML preview that can be opened and checked in Chrome.
charts-graphs
Load this skill whenever the project contains charts, graphs, data visualizations, infographics, or any visual representation of data (bar charts, line charts, pie charts, scatter plots, dashboards). Under no circumstances render a chart without a text alternative, data table, or summary. Prioritize conveying the same…