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 buildermethods/bm-skills --skill bm-skill-buildergit clone --depth 1 https://github.com/buildermethods/bm-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/buildermethods/bm-skills/bm-skill-builder)<a href="https://agentmods.dev/skills/buildermethods/bm-skills/bm-skill-builder"><img src="https://agentmods.dev/badge/skills/buildermethods/bm-skills/bm-skill-builder/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/buildermethods/bm-skills/bm-skill-builder"><img src="https://agentmods.dev/badge/skills/buildermethods/bm-skills/bm-skill-builder.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 | $0.00078 | $0.00654 |
| Opus 5.5 | $0.00031 | $0.00262 |
| Sonnet 5.5 | $0.00016 | $0.00131 |
| Haiku 4.5 | $0.00008 | $0.00065 |
Grade A, and why
bm-skill-builder 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 13d 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bm-skill-builder
Turns a repeatable process into a well-built agent skill: instructions in plain markdown and folders, portable across any agent harness. Works for brand-new skills and for restructuring existing ones that have outgrown a single SKILL.md.
The process
- Understand the process —
steps/understand.md: ask the user to describe the process the skill is for, then infer what you can — job, inputs, artifact, raw material. - Interview the user —
steps/interview.md: design the skill with the user — description, name, inputs (if any), its own interview (if any), realistic examples (if applicable), and the step plan. Recommend-then-confirm format throughout. - Design the shape —
steps/design.md: simple or structured, per the conventions. - Build it —
steps/build.md: write the files against the conventions checklist. - Save it —
steps/save.md: ask where the skill should live — this repo's.agents/skills/, global~/.agents/skills/, or a.claudealternate — and place it there. - Verify & hand off —
steps/verify.md: run it from its saved location, then teach the user the improvement loop.
Hard rules
- At the start of every invocation of a multi-step skill, present a simple numbered overview of the process with one very short sentence per item, then immediately begin the first step without asking permission or pausing.
- A skill's instructions are plain markdown. SKILL.md and every instruction file (steps, phases, shared, reference docs) are .md — no formats a harness has to interpret. Bundled
scripts/and reference material can be whatever the job needs (a Python script, a JSON schema, a template file). Nothing harness-specific in the skill's core — it must work anywhere. - Start as simple as the process allows. Structure (steps/, phases/, shared/) must be earned by real complexity, never added on spec.
- Order lives in the orchestrator, never in the steps. SKILL.md (or a phase's own file) carries the numbering and points at each step file; step files are topic-named, order-agnostic, and say nothing about their position in the sequence.
- Removal means gone. When removing or reversing anything in a skill, delete it and every reference to it, as if it never existed — no "don't do X" replacements, notes about what changed, legacy fallbacks, or leftover examples. A skill describes only its current process.
- The full conventions live in
reference/conventions.md— read them before designing, and check the finished skill against them before handing off.
What ships with it
8 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.
- 13d ago Changed · +1 lines c7366096db5a
- 1mo ago Changed · +1 lines c93d3913443d
- 1mo ago First seen · 25 lines · 78 tokens per session scan A 1e51300a289f
bm-skill-builder is a skill published in the GitHub repository buildermethods/bm-skills (147 stars, last pushed 10d ago), licensed MIT. It adds 78 tokens to every session and 654 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.