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 konten-studio/jekardah-writer --skill platform-formatgit clone --depth 1 https://github.com/konten-studio/jekardah-writerWrote 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/konten-studio/jekardah-writer/platform-format)<a href="https://agentmods.dev/skills/konten-studio/jekardah-writer/platform-format"><img src="https://agentmods.dev/badge/skills/konten-studio/jekardah-writer/platform-format/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/konten-studio/jekardah-writer/platform-format"><img src="https://agentmods.dev/badge/skills/konten-studio/jekardah-writer/platform-format.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 | $0.00061 | $0.00752 |
| Opus 5 | $0.00030 | $0.00376 |
| Sonnet 5 | $0.00012 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
platform-format 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 today.
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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform Format
Shape an already-written draft to fit one channel's conventions. This is a structural/layout pass, not a rewrite: it never changes facts, hook wording, voice diction, or claims.
Load only what you need
- Read references/platform-specs.md for per-platform length limits, structural conventions, and split/beat rules.
Scope contract
This skill owns segmentation, ordering into platform units (tweets/slides/beats), length trimming that removes only redundancy (never claims), hashtag/CTA placement, and line-break rhythm for the target channel. It cannot own or invent facts, change the hook's wording or angle, change voice diction/register, or add claims to fit a length limit. If the draft cannot fit the platform limit without cutting a defensible proposition, stop and report the conflict instead of cutting silently.
Core workflow
- Identify the target. Confirm platform (Instagram feed/carousel, X/Twitter, LinkedIn, TikTok/Reels script, newsletter/email, or generic long-form) and any explicit constraints (thread length cap, carousel slide count, video duration).
- Load the spec. Use references/platform-specs.md for that platform's limits and conventions.
- Segment. Split the draft into the platform's native units (tweets, slides, beats, paragraphs) at natural sense-breaks — never mid-proposition.
- Trim only redundancy. If over length, cut repeated phrasing, filler transitions, or restated points first. Never cut a name, number, date, attribution, or the hook/payoff pair.
- Place CTA and hashtags/tags per the target platform's convention from the spec, using the CTA intent already locked upstream — do not invent a new CTA.
- Verify fit. Confirm every unit is within the platform's limit and the split reads naturally stand-alone (each tweet/slide should not require the next to make sense on its own, where the platform expects that).
Composition contract
What ships with it
2 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.
- today First seen · 46 lines · 61 tokens per session scan A c6c184d14139
platform-format is a skill published in the GitHub repository konten-studio/jekardah-writer (25 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 752 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 2026-09-10.
Other skills, from other repositories
ulw-research
Runs maximum-saturation research with a cooperating team, claim-graph gating, and a cited, QA'd deliverable. Use when the user explicitly asks for research or a deep investigation, including any 'ulw' research wording.
programming
Applies strict, modern language practice (typed errors, exhaustive match, TDD) for Python, Rust, TypeScript, and Go. Use for work on .py, .rs, .ts, or .go files.
refactor
Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.
ulw-execute
Executes a written Prometheus work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execute or asks to run a .omo/plans plan.
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces with screenshot evidence and a verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right.
work-with-pr
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…