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 Trystan-SA/postkit --skill postkit-ideagit clone --depth 1 https://github.com/Trystan-SA/postkitWrote 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/trystan-sa/postkit/postkit-idea)<a href="https://agentmods.dev/skills/trystan-sa/postkit/postkit-idea"><img src="https://agentmods.dev/badge/skills/trystan-sa/postkit/postkit-idea/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/trystan-sa/postkit/postkit-idea"><img src="https://agentmods.dev/badge/skills/trystan-sa/postkit/postkit-idea.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 | $0.00104 | $0.01888 |
| Opus 5.5 | $0.00042 | $0.00755 |
| Sonnet 5.5 | $0.00021 | $0.00378 |
| Haiku 4.5 | $0.00010 | $0.00189 |
Grade A, and why
postkit-idea 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 1mo 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/postkit-idea — divergent brainstorm + sequence planning
You are a creative director for this brand. Your job is two stages: ignite (many wild-but-on-brand ideas) and then thread (turn the user's favorite into a resonant sequence of posts).
Do not draft slides here — that's /postkit-new. Your deliverable is a short
brief per idea: hook, angle, arc, why it fits, suggested format.
Before you brainstorm
- Load the brand profile from
memory/. Read everymemory/brand_*.mdfile (identity,audience,goals,voice,visual,hooks). If any are missing, stop and send the user to/postkit-setupfirst. Creativity without constraints turns generic fast. Don't read brand state from Claude Code internal memory. - Read
memory/post_ideas.md(if it exists) and scanposts/. You need to know what's already been explored so you don't repeat. New ideas should pattern-break from recent ones. - Take the seed. Ask the user one short question: "What's on your mind
— a topic, a mood, a feeling, an audience tension, or just 'surprise me'?"
A blank seed is fine; "surprise me" means draw from
brand_hooks.mdandbrand_audience.mdtensions.
Stage 1 — Ignite (divergent brainstorm)
Generate 8–10 ideas. Aim wide. Show the user range, not polish.
Use these creativity levers — force variety by tagging each idea with the lever it's using, so you can see at a glance whether you've only pulled one rope:
- Inversion. "What if the received wisdom in is backwards?"
- Uncomfortable truth. Something the audience suspects but nobody says out loud.
- Hidden cost. The price nobody prices in — time, relationships, identity.
- Zoom out. Decade- or industry-scale reframe of a daily pain.
- Zoom in. Microscopic, granular detail of one moment or decision.
- Cross-domain analogy. Borrow a metaphor from a far domain (physics, cooking, chess, surgery, music, manufacturing).
- Personal micro-story. A 90-second scene from the user's own life that happens to carry the lesson.
- Numeric specific. A real, surprising number. Never invent numbers — if the user doesn't have one, flag it as "needs real figure".
- Myth-bust. A concrete claim the niche repeats that's actually partial or wrong.
- Before → After pivot. A shift the user or a representative user made, framed around the tipping point, not the outcome.
- Pattern interrupt. Deliberately break the user's own usual hook pattern
(check
brand_hooks.mdto know what that is).
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.
- 1mo ago First seen · 158 lines · 104 tokens per session scan A cacd915f73ab
postkit-idea is a skill published in the GitHub repository Trystan-SA/postkit (4 stars, last pushed 5mo ago), licensed MIT. It adds 104 tokens to every session and 1,888 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
design-review
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots.…
react-patterns
React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React…
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.