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 review-plansgit 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/review-plans)<a href="https://agentmods.dev/skills/blake-simpson/belmont/review-plans"><img src="https://agentmods.dev/badge/skills/blake-simpson/belmont/review-plans/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/review-plans"><img src="https://agentmods.dev/badge/skills/blake-simpson/belmont/review-plans.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 | $0.03722 |
| Opus 5 | $0.00021 | $0.01861 |
| Sonnet 5 | $0.00008 | $0.00744 |
| Haiku 4.5 | $0.00004 | $0.00372 |
Grade A, and why
review-plans 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 10d 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Belmont: Review Plans
You are reviewing the alignment between planning documents and the codebase. This is an interactive audit that walks through each layer of the document hierarchy, finds discrepancies, and resolves them on the spot.
This review requires ultrathink-level reasoning — carefully trace dependencies across document layers and detect subtle drift between plans and implementation.
Purpose
Belmont's planning workflow creates a layered document hierarchy (PR/FAQ → Master PRD/Tech Plan → Feature PRDs/Tech Plans → Tasks/Milestones). Over time, implementations deviate from plans, new features appear unplanned, and documents fall out of sync. This review closes that gap.
Critical Rules
- Planning-only — this skill modifies planning documents (PRDs, Tech Plans, PROGRESS, NOTES). It does NOT modify source code.
- Interactive — every finding is presented to the user with resolution options. Never auto-resolve.
- Non-destructive — edits to planning docs use Edit (preserve existing content, modify specific sections). Never overwrite entire files.
- Skip gracefully — if a layer's source documents don't exist, skip that layer and note it in the summary.
Forbidden Actions
- DO NOT modify any source code files
- DO NOT run builds, tests, or any compilation commands
- DO NOT create new feature directories — only suggest it as a follow-up
- DO NOT auto-resolve findings without user input
- DO NOT delete planning documents
Allowed Actions
- DO read all
.belmont/planning documents - DO read the codebase structure (tree, glob, key files referenced in tech plans)
- DO present findings interactively via
AskUserQuestion - DO edit PRDs, Tech Plans, PROGRESS, and NOTES files based on user decisions
- DO create follow-up tasks in feature PRDs and PROGRESS files
Step 1: Load All Planning Documents
Read all .belmont/ files and build an inventory:
- Check for
.belmont/directory — if it doesn't exist, tell the user to runbelmont installfirst and stop - Read
.belmont/PR_FAQ.md— note if it exists and has content - Read
.belmont/PRD.md— the master PRD (feature catalog). Extract the features table - Read
.belmont/TECH_PLAN.md— the master tech plan - Scan
.belmont/features/for subdirectories - For each feature directory, read:
PRD.md(feature requirements + tasks)TECH_PLAN.md(feature technical plan)PROGRESS.md(milestones + task tracking)NOTES.md(if it exists)
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.
- 10d ago First seen · 326 lines · 42 tokens per session scan A ab44ee78fab7
review-plans is a skill published in the GitHub repository blake-simpson/belmont (4 stars, last pushed 21d ago), licensed Apache-2.0. It adds 42 tokens to every session and 3,722 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
agentrq
Execute tasks assigned by humans or supervisor agents within a specific AgentRQ workspace. Use when you receive channel messages or need to report progress on tasks.
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.
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.