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 cosmicstack-labs/mercury-agent-skills --skill habit-formationgit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-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/cosmicstack-labs/mercury-agent-skills/habit-formation)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/habit-formation"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/habit-formation/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/cosmicstack-labs/mercury-agent-skills/habit-formation"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/habit-formation.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 | $0.00023 | $0.00553 |
| Opus 5 | $0.00012 | $0.00277 |
| Sonnet 5 | $0.00005 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
habit-formation 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 7d 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.
What it actually says
Habit Formation
Build lasting habits using evidence-based behavior change techniques.
The Habit Loop
Cue → Craving → Response → Reward
Make or Break by Changing Each Element
| Element | Make a Habit Stick | Break a Bad Habit |
|---|---|---|
| Cue | Make it obvious | Make it invisible |
| Craving | Make it attractive | Make it unattractive |
| Response | Make it easy | Make it difficult |
| Reward | Make it satisfying | Make it unsatisfying |
Implementation Strategies
Habit Stacking
"After [current habit], I will [new habit]."
Examples:
- After I pour my morning coffee, I will write 3 things I'm grateful for.
- After I brush my teeth at night, I will lay out my workout clothes.
- After I sit down at my desk, I will open my task list.
Two-Minute Rule
New habits should take <2 minutes to start:
- "Run 3 miles" → "Put on running shoes"
- "Write 500 words" → "Open my writing app"
- "Meditate 10 min" → "Sit on my meditation cushion"
Environment Design
- Want to read more? Put a book on your pillow
- Want to eat healthy? Put fruit on the counter, junk in the back
- Want to exercise? Sleep in your workout clothes
- Want to stop checking phone? Keep it in another room
Tracking & Accountability
| Method | How | Why It Works |
|---|---|---|
| Habit tracker | Check off each day | Visual progress, streak motivation |
| Accountability partner | Daily check-in | Social commitment, external consistency |
| Public commitment | Share your goal | Social pressure, identity reinforcement |
| Contract | Penalty for missing | Loss aversion is powerful |
When It Gets Hard
- Don't miss twice: One slip is a mistake, two is a new pattern
- Never skip two days in a row: The streak resets but identity stays
- Reduce scope: If 10 min is hard, do 2 min. Show up, that's the win.
- Focus on identity: "I'm a runner" beats "I need to run"
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.
- 7d ago First seen · 66 lines · 23 tokens per session scan A 988542026be1
habit-formation is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (470 stars, last pushed 16d ago), licensed MIT. It adds 23 tokens to every session and 553 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.
Other skills, from other repositories
laohan-jiaocheng
A tutorial router that selects installation and setup instructions from keywords such as claude-mem, CLAUDE.md, Gemini sidebar, GLM, or ECC. It guides the user through the selected tutorial and checks key results.
worksheet-skill
A resource for creating classroom worksheets and other printable learning materials.
koda-jetbrains-helper
A reference guide for JetBrains development environments and related products such as GIGAIDE and OpenIDE.
interview-simulator
An interview-practice tool that acts like an interviewer and asks follow-up questions about your answers. It covers behavioral, technical, and case interviews, then reviews responses using the STAR method: Situation, Task, Action, and Result.
flashcard-studio
A flashcard generator that extracts key points from plain text, Markdown, or notes and writes question-and-answer cards to an Anki-compatible CSV file. Anki is a study app that schedules reviews using spaced repetition.
obscure-tool-install-lookup
Use when a user asks how to install or use an obscure CLI tool, agent, or package and search engines are blocked, CAPTCHA-walled, or unhelpful. Resolves canonical install commands via GitHub repo search, raw README fetches, and official docs — without relying on websearch or bot-walled search engines.