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 blake-simpson/belmont --skill repairgit 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/repair)<a href="https://agentmods.dev/skills/blake-simpson/belmont/repair"><img src="https://agentmods.dev/badge/skills/blake-simpson/belmont/repair/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/blake-simpson/belmont/repair"><img src="https://agentmods.dev/badge/skills/blake-simpson/belmont/repair.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 | $0.00042 | $0.03464 |
| Opus 5 | $0.00021 | $0.01732 |
| Sonnet 5 | $0.00008 | $0.00693 |
| Haiku 4.5 | $0.00004 | $0.00346 |
Grade A, and why
repair 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.
How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Belmont: Repair
You are the repair reviewer. A PROGRESS.md has entries Belmont cannot act on, and your job is to work out what each one should say — from the repository, not from anyone's recollection.
This skill runs in two situations. Read the next two sections and decide which one you are in before doing anything else.
Mode A — the CLI called you (proposal mode)
If the prompt you were invoked with contains a REPAIR BRIEF block:
- The mechanical tier has already run. Anything the commit log settled has already been applied and is not in your brief.
- Do not edit
PROGRESS.md, or any other file. Investigate, then write the JSON proposal to the path the brief names. The CLI validates every action, applies what passes, and shows the user each edit before making it. - The brief carries the full rules and the exact JSON shape. Follow them; they are the same ones repeated under How to decide below.
Mode B — a person typed /belmont:repair (interactive mode)
Run the two tiers yourself, in this order. Do not skip tier 1 — it costs nothing and answers most of the findings without you reading a line of code.
Feature Selection
Belmont organizes work into features — each feature gets its own directory under .belmont/features/<slug>/ with its own PRD, PROGRESS, TECH_PLAN, and MILESTONE files.
Select the Active Feature
- List all feature directories under
.belmont/features/ - If features exist: read each feature's
PRD.mdfor its name and status, then ask which feature to repair, or auto-select the only one - If no features exist: tell the user to run
/belmont:product-planto create their first feature, then stop - Set the base path to
.belmont/features/<selected-slug>/
Base Path Convention
Once the base path is resolved, use {base} as shorthand:
{base}/PRD.md— the feature PRD{base}/PROGRESS.md— the feature progress tracker{base}/TECH_PLAN.md— the feature tech plan{base}/MILESTONE.md— the active milestone file{base}/MILESTONE-*.done.md— archived milestones{base}/NOTES.md— learnings and discoveries from previous sessions
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.
- 8d ago First seen · 279 lines · 42 tokens per session scan A b0b002bb0637
repair is a skill published in the GitHub repository blake-simpson/belmont (4 stars, last pushed 20d ago), licensed Apache-2.0. It adds 42 tokens to every session and 3,464 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 2026-08-31.
Other skills, from other repositories
ant
Structured, enterprise-focused design system emphasizing clarity, consistency, and efficiency for data-dense web applications.
basic
Print-inspired visual language for books, magazines, and reports with editorial grids and expressive typography.
bento
Modular grid layout with card-like blocks, clear hierarchy, soft spacing, and subtle visual contrast for organized, scannable interfaces.
fiction
A playful, energetic, cartoonesque interface inspired by friendly children's-book illustrations — warm cream backgrounds, big bold custom display typography, saturated brand color blocks, thick black outlines, generously rounded shapes.
lingo
Playful, minimal design with bright colors, rounded shapes, tactile 3D borders, and friendly illustrations for approachable interfaces.
stitch
Clean, high-contrast enterprise design for data-driven workflows with intuitive drag-and-drop patterns and structured layouts.