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 nxtg-ai/forge-plugin --skill skill-developmentgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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/nxtg-ai/forge-plugin/skill-development)<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/skill-development"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/skill-development/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/nxtg-ai/forge-plugin/skill-development"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/skill-development.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 | $0.00074 | $0.01921 |
| Opus 5.5 | $0.00030 | $0.00768 |
| Sonnet 5.5 | $0.00015 | $0.00384 |
| Haiku 4.5 | $0.00007 | $0.00192 |
Grade A, and why
Skill Development 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 12d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Development
Procedure for authoring Claude Code Agent Skills. A skill is a directory with a SKILL.md file; optional bundled scripts and reference .md files sit beside it and load only when needed.
What a skill is (one paragraph)
At startup Claude preloads only the name + description of every installed skill into its system prompt. When a task matches, Claude reads the full SKILL.md body into context. Bundled files (reference/*.md, scripts/*) are read only when the body points to them. This is progressive disclosure: metadata → body → bundled files. Design each level to be the smallest thing that lets Claude decide whether to go deeper.
Build workflow
- Start from a real gap. Author a skill only for a capability Claude currently fumbles — a workflow it gets wrong, procedural knowledge it lacks, org context it can't infer. Don't pre-write skills for hypothetical tasks.
- Create the directory + SKILL.md.
skills/<kebab-name>/SKILL.md. Directory name is the on-disk identity — don't rename it after wiring. - Write the frontmatter (see below). The
descriptionis the single highest-impact line — write it as a routing rule, not a summary. - Write the body as what to do, not narration. Numbered procedures, concrete examples, a Gotchas section.
- Keep it lean. Target under 500 lines. When it grows past that (or when some content is only relevant in a narrow sub-case), move detail into sibling
reference/*.mdfiles and link them. - Test the trigger. Give Claude a request that should fire the skill and confirm it loads. If it doesn't, the description is the problem — add the missing trigger words. Then watch it use the skill on a real task and fold successes/mistakes back into the body.
Frontmatter — valid fields only
Claude Code reads a fixed set of keys and silently ignores unknown ones (so a typo'd field just disappears — no error).
name: Skill Name # REQUIRED. Display label. Max 64 chars. Keep stable — wiring references it.
description: > # REQUIRED. The routing engine (see below). Use > or | for multi-line.
What it does. Use when <triggers>.
disable-model-invocation: true # Hide from Claude's auto-trigger AND remove description from context.
user-invocable: false # Hide from the / menu but keep in context for auto-trigger.
argument-hint: "[arg]" # Autocomplete hint for invocable skills.
allowed-tools: Read, Grep # Pre-approves these tools so the skill's procedure doesn't prompt.
# ADDITIVE only — does not restrict what's available.
context: fork # Run the skill in an isolated subagent context window.
model: sonnet # Per-skill model override (sonnet | opus | haiku).
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.
- 12d ago Changed 46bec89ee4dc
- 1mo ago First seen · 108 lines · 74 tokens per session scan A 8ac485b593cf
Skill Development is a skill published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 74 tokens to every session and 1,921 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 2026-09-03.
Other skills, from other repositories
devops-deployment
Use when setting up CI/CD pipelines, containerizing applications, deploying to Kubernetes, or writing infrastructure as code. DevOps & Deployment covers GitHub Actions, Docker, Helm, and Terraform patterns.
branchbox-devcontainer-guardrails
Use when modifying BranchBox devcontainer/bootstrap workflows, compose templates, feature env-stash behavior, or manual E2E harness/release docs. Apply issue.
helm
Version: 1.0.0 | Target Size: <100KB | Purpose: Fast reference for Helm chart development and deployment.
kubernetes
Version: 1.0.0 | Target Size: <100KB | Purpose: Fast reference for Kubernetes manifest development and deployment.
hatch3r-cli-toolbox
Category-indexed reference for 34 specialist CLI tools beyond the always-on five (ripgrep, jq, gh, fd, fzf). Use to pick the right tool for HTTP clients, ai-chat, structural-search, sed-style edits, data ops, browser automation, container ops, and more.
hatch3r-containerize
Containerizes an application through a repeatable workflow — multi-stage Dockerfile, non-root hardening, minimal base image, .dockerignore, healthcheck, local docker-compose, Kubernetes manifest basics, and an image-scan gate. Use when adding or hardening container artifacts.