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 agentmods add skills/blake-simpson/belmont/resetnpx skills add blake-simpson/belmont --skill resetgit clone --depth 1 https://github.com/blake-simpson/belmontWrote 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/blake-simpson/belmont/reset)<a href="https://agentmods.dev/skills/blake-simpson/belmont/reset"><img src="https://agentmods.dev/badge/skills/blake-simpson/belmont/reset.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00977 |
| Opus 5 | $0.00010 | $0.00489 |
| Sonnet 5 | $0.00004 | $0.00195 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
reset 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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Belmont: Reset
You are resetting the belmont state directory so the user can start a new planning session from scratch.
CRITICAL RULES
- NEVER clear files without explicit user confirmation.
- ONLY modify files in the
.belmont/directory. - Do NOT touch
.agents/, source code, or any other files.
Step 1: Read Current State
Read the following files (if they exist) and collect a summary:
.belmont/PR_FAQ.md— Check if it exists and has real content.belmont/PRD.md— Extract the product/feature name, check if it's a master feature catalog.belmont/TECH_PLAN.md— Check if it exists and has content (master tech plan).belmont/NOTES.md— Check if global notes exist.belmont/features/— Scan for feature subdirectories. For each, read its PRD.md for name and PROGRESS.md for task counts.
Optional helper:
- If the CLI is available,
belmont status --format jsoncan provide a quick task/milestone summary. Still check for MILESTONE files, TECH_PLAN, PR_FAQ, and features/ existence.
If .belmont/ does not exist or contains only empty templates and no features, tell the user there is nothing to reset and stop.
Step 2: Present Options
Present a clear summary and options:
WARNING — Reset Belmont State
========================
Product: [product name from master PRD]
PR/FAQ: [Has content / Empty]
Master PRD: [Has content / Empty]
Master Tech: [Exists / Does not exist]
Global Notes: [Exists / Does not exist]
Features:
[slug] [feature name] — [X] tasks ([Y] complete)
[slug] [feature name] — [X] tasks ([Y] complete)
...
Options:
[1] Reset a specific feature (delete its directory contents, preserve masters)
[2] Reset ALL features (clear all feature dirs, preserve masters)
[3] Full reset (everything, including masters and PR_FAQ)
[c] Cancel
WARNING: This cannot be undone.
Wait for the user's response. Do NOT proceed until you receive a reply.
Step 3: Handle Response
Option 1 — Reset specific feature:
- Ask which feature to reset (by slug or number)
- Delete all files in
.belmont/features/<slug>/(PRD.md, PROGRESS.md, TECH_PLAN.md, NOTES.md, MILESTONE.md, MILESTONE-*.done.md) - Remove the feature directory
- Update the master PRD features table to remove/mark the feature
- Report what was reset
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.
- 4d ago First seen · 98 lines · 20 tokens per session scan A 25c196e796d6
reset is a skill published in the GitHub repository blake-simpson/belmont (4 stars, last pushed 16d ago), licensed Apache-2.0. It adds 20 tokens to every session and 977 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 2026-08-31.
Other skills, from other repositories
smoke-test
End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
bootstrap
Generate a personalized SOUL.md through a warm, adaptive onboarding conversation. Trigger when the user wants to create, set up, or initialize their AI partner's identity — e.g., "create my SOUL.md", "bootstrap my agent", "set up my AI partner", "define who you are", "let's do onboarding", "personalize this AI", "make…
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer.