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 agentmods add skills/stepkar2004/init-configurator/socialsnpx skills add Stepkar2004/init-configurator --skill socialsgit clone --depth 1 https://github.com/Stepkar2004/init-configuratorWrote 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/stepkar2004/init-configurator/socials)<a href="https://agentmods.dev/skills/stepkar2004/init-configurator/socials"><img src="https://agentmods.dev/badge/skills/stepkar2004/init-configurator/socials.svg" alt="Measured on agentmods" 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 | $0.00135 | $0.01360 |
| Opus 5 | $0.00068 | $0.00680 |
| Sonnet 5 | $0.00027 | $0.00272 |
| Haiku 4.5 | $0.00014 | $0.00136 |
Grade A, and why
socials 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 3d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
socials — decide → optimize → draft → post (the human posts)
Authored 2026-07-11 from a four-source research pass: the longform-factory skill (VideoCreator2, its stage architecture and export format), a live review of real LinkedIn posts, and two web sweeps (LinkedIn algorithm, GitHub discoverability) — raw (2026-07). Platform mechanics rot fast: each platform reference separates evergreen mechanism facts from dated snapshots. Re-verify anything dated older than ~6 months before a high-stakes post.
What the user gates (hard rules)
- The user picks WHAT to post, from a shortlist — never solo.
- The user approves final wording, and their edits are canon: a later formatting or export pass must never silently regress words the user touched.
- The user does the actual posting. NEVER auto-post, never drive a browser or API to publish — the deliverable is a paste-ready package.
- Posts contain no em dashes and no en dashes (user rule — restructure the sentence instead). Repo docs keep house style; the rule is for post text only.
The workflow
| Step | What happens | Produces |
|---|---|---|
| 1. Decide | score 2-4 candidate angles on the axes below, recommend one, STOP — user picks | chosen topic + angle |
| 2. Optimize | load the platform reference; none exists → generic checklist below, offer to research + author one | constraints the draft must obey |
| 3. Draft | hook first (it must fit the platform's fold), preview digest before full text, asset brief via references/visuals.md | draft in docs/posts/ |
| 4. Post | paste-ready package (format below), user posts, outcome noted in the draft file | posted + one log line |
When the "post" is a page that just needs to be findable (a GitHub repo, a profile), decide and draft collapse — step 2 with the right reference is the whole job.
Decide axes (evidence, not vibes — cite why for each):
- Demand proof — has this angle worked for someone else, or does it answer something people actually ask?
- Substance density — enough concrete numbers, artifacts, or moments to fill it without padding? If not, the draft will starve.
- Audience payoff — who is this for and what do they walk away with?
- Timing — is there a hook now (launch, milestone, fresh lesson), or does it keep?
What ships with it
4 files 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.
- 3d ago First seen · 89 lines · 135 tokens per session scan A 310411e507e0
socials is a skill published in the GitHub repository Stepkar2004/init-configurator (1 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 1,360 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…