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 agentmods add skills/techwolf-ai/ai-first-toolkit/build-pluginnpx skills add techwolf-ai/ai-first-toolkit --skill build-plugingit clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkitWhat 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 | $0.00093 | $0.02332 |
| Opus 5 | $0.00046 | $0.01166 |
| Sonnet 5 | $0.00019 | $0.00466 |
| Haiku 4.5 | $0.00009 | $0.00233 |
Grade B, and why
build-plugin scanned grade B with 1 finding 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 2d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
| **Ship** | N/A, no marketplace. Load via `claude --plugin-dir`, or scaffold it in your skills dir (`claude plugin init`) to auto-load every session. | Marketplace repo on GitHub; entry `source: {source:"github", repo:" How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Plugin
Bundle many tools (skills, hooks, agents, MCP servers) into one installable Claude Code plugin and distribute it. The defining move of this skill: establish who the plugin is for and where it will live with AskUserQuestion before assembling anything, then tailor every phase to that answer. A personal one-project bundle and a public team marketplace share almost nothing past "assemble", so branch early and commit to the branch.
How this relates to build-mcp
build-mcp builds one MCP server: analyze a service, implement the tools, deploy, scale. build-plugin bundles many tools (including MCP servers produced by build-mcp) into a single shareable unit and distributes it. When build-mcp reaches its Distribute phase for a team or public audience, it hands off here: packaging into a plugin and listing it on a marketplace is this skill's job. Use build-mcp to make a server, then build-plugin to ship it alongside your skills, hooks, and agents.
The four phases
- Analyze: decide what tools go in the bundle, and name it.
- Assemble: build the plugin folder and manifest, test it locally with
claude --plugin-dir. - Ship: put it on a marketplace repo, on the right git host, public or private, with one-click enablement for a team.
- Maintain: versions, updates, ownership, and admin controls.
Run them in order. The AskUserQuestion answers from Phase 0 gate Ship and Maintain.
Phase 0: Establish context (AskUserQuestion, do this first)
Before assembling anything, branch on the user's context. Ask the audience question first; it is the headline decision and it cascades into everything downstream. Then ask the git host only if it is still ambiguous. Ask one question at a time.
Question 1 (always, ask first): Audience:
Use AskUserQuestion:
- header: "Audience"
- question: "Who is this plugin for? This decides where it's hosted and how it's shared."
- options:
- "Just me": personal bundle of my own tools, one machine or a couple of projects.
- "My team / org": shared internally, installed by colleagues.
- "Public / external": published openly for anyone to install.
What ships with it
4 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.
- 2d ago First seen · 112 lines · 93 tokens per session scan B b7b910202512
build-plugin is a skill published in the GitHub repository techwolf-ai/ai-first-toolkit (96 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 2,332 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
skill-check
Validate Claude Code skills against Anthropic guidelines. Use when user says "check skill", "skillcheck", "validate SKILL.md", or asks to find issues in skill definitions. Covers structural and semantic validation. Do NOT use for anti-slop detection, security scanning, token analysis, enterprise checks, or Eval Kit…
truthmark-sync
Use automatically at finish-time after functional code changes, or explicit /truthmark-sync, $truthmark-sync, or /truthmark:sync. Skip docs-only, formatting-only, behavior-preserving renames, missing config, and no-code changes. Not for doc-first realization or manual topology design.
truthmark-realize
Use when the user explicitly asks to realize Truthmark truth docs into code, including /truthmark-realize, $truthmark-realize, or /truthmark:realize. Not for syncing docs after code changes, documenting existing code, topology repair, or truth audits.
truthmark-structure
Use when routing or truth ownership is missing, stale, broad, overloaded, catch-all, unrouteable, mixed-owner, needs split/repair, or needs new area setup. Not for documenting implemented behavior, syncing a code diff, or realizing docs into code.
truthmark-check
Use when the user asks to audit repository truth health, routing, ownership, or canonical docs. Not for normal lint/test/typecheck/code-review verification, finish-time Sync, or silently rewriting docs.