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 aryaminus/socials-assistant --skill publish-packagegit clone --depth 1 https://github.com/aryaminus/socials-assistantWrote 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/aryaminus/socials-assistant/publish-package)<a href="https://agentmods.dev/skills/aryaminus/socials-assistant/publish-package"><img src="https://agentmods.dev/badge/skills/aryaminus/socials-assistant/publish-package/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/aryaminus/socials-assistant/publish-package"><img src="https://agentmods.dev/badge/skills/aryaminus/socials-assistant/publish-package.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 | $0.00067 | $0.00729 |
| Opus 5 | $0.00034 | $0.00365 |
| Sonnet 5 | $0.00013 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
publish-package 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 8d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
publish-package — green light → ready to post → measured
The agent owns packaging and measurement; the human posts (posting automation is deliberately out of scope — see docs/CAPABILITIES.md).
Step 1 — Assemble the package (stage: approved)
socials-mcp:profile_get(tone, keywords) +socials-mcp:pipeline_list(stage: "approved") to find the item.- Generate the package:
- Title options (3) — keyword-front-loaded, ≤80 chars, pattern-matched to the creator's top_content titles.
- Caption — hook line + 1–2 lines of context + CTA matching tone_notes; disclosure (#ad / #sponsored) FIRST if branded, per brief.
- Hashtags (5–8) — mix: 2 niche keywords from profile, 2 proven (appear in past top titles/captions), 2 broad-reach; check they're real words, no ban-list tags.
- Best posting window — data-driven:
vault_queryday-of-week viewsSELECT strftime('%w', date) AS dow, sum(value) AS v FROM account_metrics am JOIN snapshots s ON s.id=am.snapshot_id JOIN accounts a ON a.id=s.account_id WHERE a.platform=? AND am.metric='views' AND am.date IS NOT NULL GROUP BY dow ORDER BY v DESC→ recommend top day(s) + evening preference if the creator's audience skews after-work hours (note when data is thin: say "no strong signal; default to your usual slot").
- Present the package for approval; on go-ahead,
socials-mcp:pipeline_update→ keepapproved, attach package innotes.
Step 2 — At posting time (human posts)
Hand over the final copy-paste block (title / caption / tags). After they confirm it's live: pipeline_update → stage: "posted" with post_url and posted_at.
Step 3 — Measure (the part nobody does)
- 48h check-in: find the video via
top_content(days: 2) orvault_queryon title match; report early velocity vs the creator's median (top_contentdays: 30,limit: 20→ median views). Flag if it's tracking below half the median at 48h so there's time to fix the title/cover. - 7-day verdict: views, ER, watch time vs median → append a one-line outcome to the pipeline item notes (
pipeline_update), setstage: "measured". - If sponsored: mirror the outcome to the linked outreach entry (
outreach_log_updatenotes) — that's the case study for the next pitch (media-kit skill picks it up).
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.
- 8d ago First seen · 38 lines · 67 tokens per session scan A 52f6619d270e
publish-package is a skill published in the GitHub repository aryaminus/socials-assistant (0 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 729 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 skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
grounded-citations
Ground answers and documents in cited, verifiable sources.
hermes-agent-skill-authoring
Author in-repo SKILL.md files: frontmatter and structure.
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
flash-attention
Speed up long-sequence transformer training and inference.