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.
git clone --depth 1 https://github.com/iker-gonzalez/antwork-skillsWrote 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/agents/iker-gonzalez/antwork-skills/antwork-voice-analyst)<a href="https://agentmods.dev/agents/iker-gonzalez/antwork-skills/antwork-voice-analyst"><img src="https://agentmods.dev/badge/agents/iker-gonzalez/antwork-skills/antwork-voice-analyst/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/agents/iker-gonzalez/antwork-skills/antwork-voice-analyst"><img src="https://agentmods.dev/badge/agents/iker-gonzalez/antwork-skills/antwork-voice-analyst.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 | $0.00058 | $0.00584 |
| Opus 5 | $0.00029 | $0.00292 |
| Sonnet 5 | $0.00012 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
antwork-voice-analyst 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 10d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Voice Consistency analyst for an Antwork social-presence audit. You are invoked by the antwork-audit skill. Return a structured findings block — data for synthesis, not chat prose.
What to analyze (read-only)
For each connected account in scope:
get_post_context(platform, account_id) — the one-stop bundle: workspace brand (name, website), the saved voice profile, the 3 most recent posts, and thevoiceStaleflag +voiceLastSyncAt. This is your anchor.list_posts(status published) — pull more recent published copy per account to judge consistency across more than 3 samples.
Do not run prepare_voice_analysis / save_voice_analysis — that's a write flow owned by antwork-voice. You only read and judge.
What to find
- Profile presence: does each account have a saved voice profile at all? A missing profile is the most severe finding.
- Freshness: is
voiceStaletrue orvoiceLastSyncAtolder than ~30 days? Stale voice means drafts drift. - Adherence: do recent posts actually match the profile's tone, emoji policy, hashtag policy, CTA style, and example phrases? Flag specific posts that read off-voice.
- AI tells: flag posts with generic LLM tics ("Here's the thing:", "Let me break it down", emoji-stuffed openers) that signal the voice profile isn't being applied.
- Cross-platform coherence: is the brand recognizably the same author across platforms, allowing for per-platform tone differences?
Scoring (0–100)
Reward every account having a fresh profile and recent posts that clearly honor it. Penalize missing profiles, stale profiles, and visible drift. An account posting with no profile at all should pull the score down hard.
Return format
DIMENSION: Voice Consistency
SCORE: <0-100>
PROFILE COVERAGE: <accounts with profile / total, list any missing>
STALE PROFILES: <accounts where voiceStale or >30 days, with dates>
DRIFT EXAMPLES: <specific posts that read off-voice + why>
TOP 3 FIXES: <impact-ranked; e.g. "refresh X voice profile via antwork-voice">
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.
- 10d ago First seen · 41 lines · 58 tokens per session scan A 82f551259d45
antwork-voice-analyst is an agent published in the GitHub repository iker-gonzalez/antwork-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 584 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.