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-campaigngit 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-campaign)<a href="https://agentmods.dev/skills/iker-gonzalez/antwork-skills/antwork-campaign"><img src="https://agentmods.dev/badge/skills/iker-gonzalez/antwork-skills/antwork-campaign/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-campaign"><img src="https://agentmods.dev/badge/skills/iker-gonzalez/antwork-skills/antwork-campaign.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 | $0.00103 | $0.01015 |
| Opus 5 | $0.00051 | $0.00508 |
| Sonnet 5 | $0.00021 | $0.00203 |
| Haiku 4.5 | $0.00010 | $0.00102 |
Grade A, and why
antwork-campaign 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running a campaign with Antwork
A campaign is a sequence of posts, each bound to one account, all sharing a campaign_id, scheduled across days toward a single goal. The work is to design the arc first, get approval, then create and schedule the sequence. This workflow codifies the mistakes assistants make when coordinating multi-post pushes.
1. Define the campaign before drafting
Pin down the brief before any copy. Capture it in templates/campaign-brief.md:
- Goal — what the campaign should achieve (signups, attendance, sales, awareness) and the single success metric.
- Window & cadence — start/end dates and how many posts on which days.
- Audience & key message — the through-line every post reinforces.
- Platforms/accounts — which
account_ids (checklist_social_accounts; skip unhealthy tokens).
For launch-shaped campaigns, use templates/launch-week.md for the classic arc: pre-launch teasers → launch-day push → follow-up / social proof.
2. Pull context and design the arc
get_optimal_posting_times— default slots and timezone.get_calendar(date_from, date_to)— so the campaign weaves around existing posts, not on top of them.get_post_context(platform, account_id)per account — voice, brand,voiceStale. Refresh stale voices (viaantwork-voice) before drafting a multi-day sequence.
Design the sequence so each post has a distinct job (tease → reveal → proof → last call), not five rewordings of the same announcement.
3. Present the sequence as a plan — and wait
Present the full sequence as a numbered plan and stop for explicit approval before creating anything. One row per post:
# | date · time (tz) | account / platform | role in arc | hook | goal
Editing a 7-post plan is far cheaper than editing 7 drafts. Don't call create_post during planning.
4. Create the sequence under one campaign_id
Generate one campaign_id for the whole push. For each post in the approved sequence:
create_post(text, account_id, hashtags?, goal="<per-post goal>", campaign_id="<shared-id>").
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 · 63 lines · 103 tokens per session scan A c2a0446a074e
antwork-campaign is a skill published in the GitHub repository iker-gonzalez/antwork-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 1,015 once invoked, about $0.0005 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.