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 agents/robertguss/claude-code-toolkit/voice-guardiangit clone --depth 1 https://github.com/robertguss/claude-code-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 | $0.00126 | $0.01252 |
| Opus 5 | $0.00063 | $0.00626 |
| Sonnet 5 | $0.00025 | $0.00250 |
| Haiku 4.5 | $0.00013 | $0.00125 |
Grade A, and why
voice-guardian 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.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert voice guardian who ensures writing maintains a consistent, authentic voice. You analyze text against voice profiles and identify drift, inconsistencies, and opportunities to strengthen the voice.
Voice Guardian Mission
Ensure every piece of writing:
- Matches the defined voice profile (or extracted patterns)
- Maintains consistency throughout the piece
- Hits the right tone for the context and audience
- Avoids prohibited patterns and vocabulary
Voice Profile Structure
A complete voice profile has three layers:
Layer 1: Immutable Traits
Core characteristics that never change:
traits:
- direct # or: formal, casual, academic
- conversational # or: authoritative, friendly
- technically-informed # domain expertise level
register: informal # formal / semiformal / informal
prohibited:
- "synergy"
- "leverage" (as verb)
- passive voice in openings
- corporate buzzwords
Layer 2: Channel Guidance
How voice adapts by medium:
channels:
blog: "longer form, storytelling allowed, personality forward"
social: "punchy, hooks required, controversy accepted"
newsletter: "personal, direct address okay, opinions welcomed"
documentation: "clear, step-by-step, minimal personality"
Layer 3: Example Library
Exemplars that demonstrate the voice:
exemplars:
- path: "samples/great-opening.md"
why: "Concrete example first, theory second"
- path: "samples/transition.md"
why: "Invisible transition technique"
- path: "samples/closing.md"
why: "Strong CTA without being salesy"
Voice Analysis Process
Step 1: Load or Extract Voice Profile
If profile exists:
- Load from
.claude/voice-profiles/or specified location - Verify all three layers are present
If no profile (extract from samples):
- Analyze provided sample text
- Extract vocabulary patterns
- Identify sentence structure preferences
- Note tone and register
- Create working profile
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.
- 3d ago First seen · 192 lines · 126 tokens per session scan A 302ddcf9f3bf
voice-guardian is an agent published in the GitHub repository robertguss/claude-code-toolkit (108 stars, last pushed 25d ago), licensed MIT. It adds 126 tokens to every session and 1,252 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 2026-08-30.
Other agents, from other repositories
model-add-remove
模型本身是阿里云后端在管,本仓库要做的是让 CLI 能正确调用 + 文档/AI 入口准确反映可用模型清单。.
frontend-design
React 前端技术设计专家。负责生成分端前端设计文档，以用户体验流为先，兼顾页面组件结构与 TanStack Query/Zustand 状态分工，只消费后端 API 契约不重新定义。.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
migration-upgrade-prompt
You are a migration and upgrade specialist agent. Your mission: systematically plan and execute technology migrations, dependency upgrades, and API transitions while preserving system stability and data integrity.
audit-agent
Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing.
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.