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/trystan-sa/postkit/postkit-reviewnpx skills add Trystan-SA/postkit --skill postkit-reviewgit clone --depth 1 https://github.com/Trystan-SA/postkitWhat 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 | $0.00085 | $0.01428 |
| Opus 5 | $0.00043 | $0.00714 |
| Sonnet 5 | $0.00017 | $0.00286 |
| Haiku 4.5 | $0.00009 | $0.00143 |
Grade A, and why
postkit-review 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/postkit-review — three-lens critique
You review a post draft (one or more slides) against the user's brand and design system, surfacing the changes that will materially improve performance.
Do not rewrite the post yourself. Your job is to identify issues and
propose specific fixes so the user (or the next run of /postkit-new) can
apply them.
Inputs
- The target post folder (default: most recently modified
posts/<slug>/). If ambiguous, ask. - The brand profile in
memory/— read everymemory/brand_*.mdfile at the project root:brand_identity.md,brand_audience.md,brand_goals.md,brand_voice.md,brand_visual.md,brand_hooks.md. If any are missing, stop and send the user to/postkit-setup. Don't read brand state from Claude Code internal memory. theme.cssat the project root — palette, tokens, component classes.- Any review logs left by a previous
/postkit-reviewrun inposts/<slug>/review.md— don't repeat findings the user already addressed.
Read all slide files, post.json, and every caption*.md file in the
post folder before forming opinions. Each caption file targets a specific
platform (filename pattern caption-<platform>.md); critique each one
against that platform's length and formatting conventions, not just the
brand voice. Flag a caption that ignores its platform's norms (e.g. a
LinkedIn-length caption saved as caption-x.md, or hashtag spam on
LinkedIn) as HIGH.
Alt text check. Any post with slides must have an ## Alt text section
in each caption file with one bullet per slide. Flag missing alt text as
HIGH (accessibility regression). Also flag alt copy that just repeats the
caption, exceeds ~125 chars, uses emojis/hashtags, or describes the
strategic purpose instead of what's visually on the slide — these as
MEDIUM.
Three lenses, one pass
Do all three in the same response. Don't spawn sub-agents.
1. Strategy
- Hook strength. Does slide 1 stop a thumb in <1s? Is it specific, or generic enough to belong to any account?
- Angle. Is this the most compelling framing (myth-bust vs. listicle vs. story vs. hot take)?
- Format fit. Right slide count? Too much padding, or too rushed?
- Value arc. Does each slide build on the previous? Any filler?
- Audience fit. Will the segment in
brand_audience.mdactually care? Right level? - Goal alignment. Does the CTA match the primary outcome in
brand_goals.md?
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 First seen · 131 lines · 85 tokens per session scan A 7846c9868139
postkit-review is a skill published in the GitHub repository Trystan-SA/postkit (4 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 1,428 once invoked, about $0.0004 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.