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 HuntsDesk/ve-kit --skill build-agentsgit clone --depth 1 https://github.com/HuntsDesk/ve-kitWrote 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/huntsdesk/ve-kit/build-agents)<a href="https://agentmods.dev/skills/huntsdesk/ve-kit/build-agents"><img src="https://agentmods.dev/badge/skills/huntsdesk/ve-kit/build-agents/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/huntsdesk/ve-kit/build-agents"><img src="https://agentmods.dev/badge/skills/huntsdesk/ve-kit/build-agents.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 | $0.00117 | $0.04296 |
| Opus 5.5 | $0.00047 | $0.01718 |
| Sonnet 5.5 | $0.00023 | $0.00859 |
| Haiku 4.5 | $0.00012 | $0.00430 |
Grade A, and why
build-agents 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 7d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build-agents — interview the codebase, then build its specialists
Most projects do not deserve forty agents. Most deserve two to five, plus the two read-only role agents. This skill finds which, using evidence from the repo rather than a wish list, and then writes agent files that actually register and actually carry knowledge.
Companion to review-agents, which audits a roster that already
exists. This one creates. Schema authority: ../_shared/anthropic-configuration-guide.md.
Model/effort authority: ../_shared/review-checklist.md § Model + effort rubric.
When to invoke
/build-agentstyped directly- "What agents should this project have?" / "Set up specialists for this repo"
- A new service, package or product surface landed and nothing owns it
- A generalist keeps getting one area wrong in the same way
Not for: changing an existing agent's model or effort (that is a fleet-tier job), rewriting
an agent's prompt body (edit the file), or auditing the roster (/review-agents).
Non-negotiables
- Search before creating. Read every existing
.claude/agents/*.mdfirst. If a domain is already owned — even partly — the answer is "extend that agent", never a second file. Never createfoo-specialist-v2,foo-specialist-new, orfoo-specialist-2. - A multi-line
descriptionMUST be a YAML block scalar (description: |). Without it, YAML parsing stops at the first blank line, the<example>blocks become invalid top-level keys, and the harness silently drops the agent. The file sits on disk looking fine and is not invocable. This is the single most common way a new agent fails. model:is an ALIAS, never a dated ID. An alias inherits the next model release for free; a pinned ID turns a free upgrade into a fleet-wide migration.- Review/consolidation agents are read-only — deny
Write,EditandNotebookEdit. - Propose few. Read Step 2's sizing rule before naming a single candidate.
What ships with it
1 file 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.
- 7d ago Changed · +1 lines 1339175f236c
- 10d ago First seen · 298 lines · 117 tokens per session scan A 37853da3a1d3
build-agents is a skill published in the GitHub repository HuntsDesk/ve-kit (3 stars, last pushed 7d ago), licensed MIT. It adds 117 tokens to every session and 4,296 once invoked, about $0.0005 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 2026-09-21.
Other skills, from other repositories
python-debugging
Use this skill when fixing failing Python tests.
repo-scan
Fast orientation for a new codebase.
safe-refactor
Refactor checklist with guardrails.
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.