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 iker-gonzalez/antwork-skills --skill antwork-voicegit 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/skills/iker-gonzalez/antwork-skills/antwork-voice)<a href="https://agentmods.dev/skills/iker-gonzalez/antwork-skills/antwork-voice"><img src="https://agentmods.dev/badge/skills/iker-gonzalez/antwork-skills/antwork-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/iker-gonzalez/antwork-skills/antwork-voice"><img src="https://agentmods.dev/badge/skills/iker-gonzalez/antwork-skills/antwork-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 | $0.00111 | $0.01054 |
| Opus 5 | $0.00056 | $0.00527 |
| Sonnet 5 | $0.00022 | $0.00211 |
| Haiku 4.5 | $0.00011 | $0.00105 |
Grade A, and why
antwork-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 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building voice profiles in Antwork
A voice profile is Antwork's per-account fingerprint of how someone writes — tone, vocabulary, emoji/hashtag habits, CTA patterns. It is the ground truth every drafting skill reads before writing copy. A stale or missing profile is the #1 reason Antwork drafts read as generic AI. This skill captures and refreshes it correctly.
0. One profile PER account, not per user
Voice lives on the social account (save_voice_analysis takes account_id), not on the workspace or the user. A founder's personal LinkedIn voice is not their company X voice. Analyze and save each account separately. Never copy one account's profile onto another.
1. Check staleness before doing anything
Call get_post_context(platform, account_id). It returns the current profile plus two signals:
voiceStale: true— profile is missing, older than 30 days, or its status isn'tcompleted.voiceLastSyncAt— when it was last built.
If voiceStale is false and the user just wants to draft, you're done — hand back to antwork-poster. Only run the analysis loop below when the profile is stale, missing, or the user explicitly asks to refresh it.
2. Fetch posts for analysis — prepare_voice_analysis
Call prepare_voice_analysis(platform, account_id, max_posts) (default 50; range 5–100). It returns the account's recent posts plus the analysis schema you must fill.
LinkedIn personal accounts can't fetch their own posts — the r_member_social scope is closed. If the response signals unsupportedFetch, fall back to the account's Antwork-published posts instead (posts shipped through Antwork are readable). If there aren't enough of those yet, tell the user the profile will be thin and ask them to paste 3–5 representative posts so you have material to analyze — don't fabricate a voice from nothing.
3. Analyze the posts yourself, against the returned schema
You do the analysis with your own reading — there is no separate model call. Read the posts and extract, matching the schema fields prepare_voice_analysis returned:
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 · 57 lines · 111 tokens per session scan A 21cd5e2ccce7
antwork-voice is a skill published in the GitHub repository iker-gonzalez/antwork-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 1,054 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
ib-trailing-stop
Server-side trailing stop management for stocks and naked LEAPS in IB. Places native TRAIL orders that auto-ratchet the stop as price climbs. Dry-run by default. Requires TWS or IB Gateway running locally.
ib-trades-history
Fetch trade executions from Interactive Brokers filtered by account, date range, or symbol. Supports live API (7 days history) and FlexReport (full history). Use when user asks about their trades, executions, or transaction history. Requires TWS or IB Gateway running locally.
fundamentals
Get fundamental financial data including financials, earnings, and key metrics. Use when user asks about financials, earnings, revenue, profit, balance sheet, income statement, or company fundamentals.
ib-collar
Generate tactical collar strategy reports for protecting PMCC positions through earnings or high-risk events. Requires TWS or IB Gateway running locally.
ib-portfolio-action-report
Generate a comprehensive portfolio action report with earnings dates and risk assessment. Use when user asks for portfolio review, action items, earnings risk, or position management across IB accounts. Requires TWS or IB Gateway running locally.
report-stock
Generate comprehensive stock analysis report (PDF or markdown) with trend, PMCC, and fundamental analysis.