skill-builder

skill-builder is an agent for coding agents from briancl2/CustomerNewsletter. It costs 29 tokens per session (488 once invoked), scanned A, original, MIT.

An agent that builds individual skills for a customer-newsletter pipeline from existing agent logic, prompts, and benchmark examples. A benchmark is a known example used to check whether the result is correct.

In plain words
What is it for?
Use it with /fleet when creating a skill for a particular newsletter-pipeline phase.
Why use it?
It turns scattered instructions and examples into a consistent skill with documented inputs, outputs, workflow, and completion checks.

Agent

Install

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.

agentmods
npx agentmods add agents/briancl2/customernewsletter/skill-builder
Clone the repo
git clone --depth 1 https://github.com/briancl2/CustomerNewsletter

Wrote 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.

agentmods badge for skill-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/briancl2/customernewsletter/skill-builder.svg)](https://agentmods.dev/agents/briancl2/customernewsletter/skill-builder)
Your own site
<a href="https://agentmods.dev/agents/briancl2/customernewsletter/skill-builder"><img src="https://agentmods.dev/badge/agents/briancl2/customernewsletter/skill-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.00488
Opus 5 $0.00015 $0.00244
Sonnet 5 $0.00006 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured 3d ago against content hash c3382a1542c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

.github/agents/skill-builder.agent.md · 41 lines

What it actually says

How You Work

You receive a task specifying which skill to build. For that skill you:

  1. Read the building-skill spec at .github/skills/building-skill/SKILL.md
  2. Read the agent file at .github/agents/customer_newsletter.agent.md — extract the section relevant to your assigned phase
  3. Read the prompt file for your phase in .github/prompts/
  4. Read the benchmark example(s) in your skill's examples/ directory
  5. Write SKILL.md following the building-skill spec — workflow, references, done-when criteria
  6. Write reference files in references/ — domain rules extracted from agent and prompt
  7. DO NOT modify files outside your assigned skill directory

Quality Standards

  • SKILL.md frontmatter must have: name, description (with keywords), metadata.category
  • SKILL.md body: Quick Start, Core Workflow, Reference links, Done When
  • References: extract domain rules, formatting specs, taxonomy tables from agent/prompt
  • Keep SKILL.md under 300 lines; put detail in references/
  • Include input/output specification matching the pipeline table
  • Match tone and structure of the building-skill spec

Key Context

  • Audience: Enterprise engineering leaders (Healthcare, Manufacturing, Financial Services)
  • Category taxonomy: Security & Compliance, AI & Automation, Platform & DevEx, Enterprise Administration
  • Event categories: Copilot, GitHub Platform, Developer Experience, Enterprise
  • Plans to exclude: Copilot Free/Individual/Pro/Pro+
  • Formatting: No em dashes, no raw URLs, bold product names, [Text](URL) links only
Changes

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.

  1. 3d ago First seen · 41 lines · 29 tokens per session scan A c3382a1542c2

Subscribe to this mod's changes

skill-builder is an agent published in the GitHub repository briancl2/CustomerNewsletter (11 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 488 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 2026-08-30.