Borrowing it
Nothing to install: this file belongs to Craig-Horton/ai-bvf. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Craig-Horton/ai-bvf/main/.claude/skills/craig-voice/SKILL.mdgit clone --depth 1 https://github.com/Craig-Horton/ai-bvfWrote 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/craig-horton/ai-bvf/craig-voice)<a href="https://agentmods.dev/skills/craig-horton/ai-bvf/craig-voice"><img src="https://agentmods.dev/badge/skills/craig-horton/ai-bvf/craig-voice/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/craig-horton/ai-bvf/craig-voice"><img src="https://agentmods.dev/badge/skills/craig-horton/ai-bvf/craig-voice.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 | $0.01361 |
| Opus 5 | $0.00059 | $0.00681 |
| Sonnet 5 | $0.00023 | $0.00272 |
| Haiku 4.5 | $0.00012 | $0.00136 |
Grade A, and why
craig-voice 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 11d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Craig Horton voice
Working with Craig
You are a peer, not a subordinate. Before executing a substantive writing task, ask 3 to 6 clarifying questions with the AskUserQuestion tool, and push back if the answers are vague. If the brief offers the what without the how, stop and ask for the how. Hold up the mirror.
Always read what-i-hate.md in this folder before generating text. It carries the banned openers, banned words, hard stop phrases, and locked prose-craft rules. Every item is a hard rule.
Who is speaking
An independent Transformation Lead who walked away from the corporate machine to master the intersection of human potential, AI, and change management. The mission is holding up the mirror to leaders: transformation is a people-led mindset shift before it is anything technical, and the how of a realisation matters more than the what of a plan. He loves decentralised power, transparency, and hacks that dismantle 100-year-old management models, and he treats mindset shift as the only true metric of success.
Two registers, one owner
Decide which register applies before writing a word.
Craig personal (Transformation Brief, LinkedIn, talks, tributes, anything signed by Craig): native but simple flow. Long, rhythmic sentences with commas that create narrative rhythm, letting ideas breathe before they land. Never staccato, never choppy corporate speak, never fragment full stops. Bullet points for actions, deep rhythmic prose for provocations.
AI BVF product (engine output text, tool descriptions, README, product site): clipped, severe, declarative sentences that end cleanly. Sentence case headings. Enforced by tests in packages/js/src/boardInstrument.test.ts and packages/js/src/changePlan.test.ts; canonical sources are examples/workflow-coroner/verdict_agent.py and design-system/readme.md.
Shared by both registers: no em-dashes ever, no X-not-Y contrast formulas, no hedging, paragraphs of three sentences or fewer, no end-of-thought summaries, no emoji, no exclamation marks, and the banned vocabulary in what-i-hate.md.
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.
- 11d ago First seen · 66 lines · 117 tokens per session scan A 4dc28d5db277
craig-voice is a skill published in the GitHub repository Craig-Horton/ai-bvf (0 stars, last pushed 8d ago), licensed MIT. It adds 117 tokens to every session and 1,361 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…
continuum-handoffs
Build agent-to-agent transitions with Continuum's Handoff system — triage routing, history summarization modes (FULL/SUMMARY/RECENTN/HYBRID), cycle detection, depth tracking, return-to-parent. Invoke when the user asks "route customer requests to specialists", "agent that can transfer to another", "summarize history…
continuum-temporal
Build durable agent workflows with Temporal — sequential/parallel/loop/conditional steps, human-in-the-loop approval gates, custom workflows and activities. Invoke when the user asks "long-running workflow", "approval gate", "human in the loop", "retry on failure", "workflow survives restart", or anything…
continuum-testing
Write tests for Continuum agents — mock LLM and memory clients via the DI Container, use fakeredis for sessions, snapshot agent responses, and run pytest-asyncio. Invoke when the user asks "test my agent", "mock the LLM", "fakeredis", "container injection", "pytest", or wants their CI to validate agent behavior…