Goose Skills is a library of workflows and data APIs that lets coding agents handle growth and go-to-market work such as advertising, social media, content, SEO, lead generation, and customer research. It is intended for teams using Claude Code, Cursor, Codex, and similar agents. The catalogue entries are its reusable skills.
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 gooseworks-ai/goose-skills --skill run-organic-social-account-auditgit clone --depth 1 https://github.com/gooseworks-ai/goose-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/gooseworks-ai/goose-skills/run-organic-social-account-audit)<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/run-organic-social-account-audit"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/run-organic-social-account-audit/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/gooseworks-ai/goose-skills/run-organic-social-account-audit"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/run-organic-social-account-audit.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 | $0.00081 | $0.01102 |
| Opus 5.5 | $0.00032 | $0.00441 |
| Sonnet 5.5 | $0.00016 | $0.00220 |
| Haiku 4.5 | $0.00008 | $0.00110 |
Grade A, and why
run-organic-social-account-audit 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 2d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Account audit
Run before the first calendar, and lightly (reconciliation only) on later runs.
1. Which accounts exist and what each is for
gooseworks:brand_readsections: ["accounts","sources","organic"].organic.own_accountslists the brand's own TikTok/IG handles.sourceslists saved public sources, includingrelationship: selfsocial accounts.accountslists connected accounts.gooseworks:social_account_list: the TikTok/IG accounts the product manages, with their setup status. Read each withgooseworks:social_strategy_get(pillars, voice, rules, plug-ratio cap).- The brain has no record of LinkedIn, X, Threads, YouTube, Pinterest or Facebook accounts today, so check
social/accounts.mdin the workspace for a previous run's answers. Ask only for what is still missing: handles, which ones matter, brand vs founder, who approves founder posts, the time zone, the tool they post from, their free windows for the first hour after posting.
2. What has worked (per account)
- TikTok/IG:
own_postsfrombrand_read organicgive caption,posted_at, views, likes and comments.gooseworks:social_analytics_getadds more for managed, connected accounts (it saysnot_availableotherwise). - More history, or LinkedIn, X and Threads: read the account's own posts through the proxy (the
marketing-data-accessskill (../marketing-data-access/SKILL.md); verified endpoints only, as listed in../run-organic-social/references/voice-card.md). Use the author's own posts only. For X:/v1/twitter/profile, then/v1/twitter/user-tweets(popular posts, not the newest: checkcreated_at; the numbers are inlegacy). This runs under thespend-gateskill (../spend-gate/SKILL.md) branch B: one yes to a ceiling, asked in the draft-report message (SKILL.md step 2), with the probe run inside it and every charge logged. Without the yes: the public profile in the host browser, or 5–10 pasted posts. - State the window you actually got (e.g. "7 IG posts, Oct 5–12"). The server returns recent posts only, and some captions come back cut off mid-word: flag those.
- Rank by engagement relative to the account's own median, not absolute numbers. For the top and bottom posts (5 each with 15+ posts, 3 each below that), note the likely why: hook, format, topic, person featured, length, time.
- Note efficacy or other claims in past captions that are not signed off, so drafts don't copy them.
- Cadence actually kept: posts per week over the window you have (up to ~8 weeks). Say how long the window is.
- Best posting slots: day and hour (in the account's time zone; ask it if unknown, since the server gives UTC) of the top performers. With fewer than ~10 posts, use the account's own usual posting times as the starting guess (label it so), not generic charts.
- Competitor and category references:
gooseworks:social_inspiration_search, thenbrand_read organic.competitor_top_posts. These are for formats and hooks only; never copy them. Skip any that are clearly outside the brand's category (a mis-resolved competitor).
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.
- 2d ago Changed fb1df6d62c89
- 7d ago First seen · 44 lines · 81 tokens per session scan A dd7e03791806
run-organic-social-account-audit is a skill published in the GitHub repository gooseworks-ai/goose-skills (1,271 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 1,102 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-21.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…