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 goodharts-lawgit 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/goodharts-law)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/goodharts-law"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/goodharts-law/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/goodharts-law"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/goodharts-law.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.01827 |
| Opus 5 | $0.00046 | $0.00914 |
| Sonnet 5 | $0.00018 | $0.00365 |
| Haiku 4.5 | $0.00009 | $0.00183 |
Grade A, and why
goodharts-law 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goodhart's Law
Overview
Goodhart's Law: when a metric controls behavior, people optimize the metric rather than the underlying goal. Formulated by economist Charles Goodhart (1975) on UK monetary policy; sharpened by Marilyn Strathern (1997): "When a measure becomes a target, it ceases to be a good measure." Four failure mechanisms (Manheim & Garrabrant 2018): Regressional, Extremal, Causal, Adversarial. Countermeasure is always multi-metric + audit + rotation.
Composes with feedback-loops, principal-agent, okr-goal-setting, survivorship-bias.
When to Use
- A KPI is being introduced or its weight is increasing in performance evaluation
- A metric is "improving" without corresponding improvement in the underlying goal
- People are visibly optimizing for a number rather than the work it was meant to track
- Algorithmic optimization is producing outcomes the designers didn't intend
- Resource allocation is driven by a single composite score or ranking
- An AI model, benchmark, or engagement metric is being optimized (or used to justify AI capex / adoption / AI-native competition) and the score is rising faster than real capability or user value
Not when: metric and goal are identical; stakes too low for gaming; metric is purely descriptive with no reward/punishment; question is which metric to use, not whether the measurement-reward system is sound.
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete metric or system → run The Process directly.
- Coach mode: user is unfamiliar or has 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.
- One-line: before relying on a metric to control behavior, predict how people will game it — choose the system that survives that prediction.
- Check fit: if the metric is purely descriptive (no reward attached), Goodhart's law doesn't apply yet.
- Elicit the specific metric and the underlying goal: what's being measured? What's the actual outcome you care about?
[WAIT — do not advance until user responds]
- One question at a time: proxy gap? How would a clever agent game this? Which Goodhart category? What countermeasure fits?
[WAIT — do not advance until user responds]
- Close: name the gaming-resistant design (multi-metric, audit, rotation, paired-constraint) + monitoring schedule.
[WAIT — do not advance until user responds]
What ships with it
3 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 · 125 lines · 92 tokens per session scan A b3e6321ddf6a
goodharts-law is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 92 tokens to every session and 1,827 once invoked, about $0.0005 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
edge-tts
Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
tianqi
A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.
compliance-check
Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…
plan-payroll
Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…
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…