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 vidhunnan/agentic-skills --skill post-setupgit clone --depth 1 https://github.com/vidhunnan/agentic-skillsWrote 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/vidhunnan/agentic-skills/post-setup)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/post-setup"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/post-setup.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 5.1 | $0.00112 | $0.03207 |
| Opus 5 | $0.00056 | $0.01604 |
| Sonnet 5 | $0.00022 | $0.00641 |
| Haiku 4.5 | $0.00011 | $0.00321 |
Grade C, and why
post-setup scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
2. **Exists** → Read; search for the literal `<!-- BEGIN skill:post-setup -->`. How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
post-setup
Builds the tier the working-in-public family writes into, and captures the two profiles the rest of the family reads: how your posts sound, and how your frames look.
Without a voice file a drafting skill falls back on the model's defaults, which is LinkedIn announcement copy — em dashes, "excited to share", emoji bullets, a hashtag stack — recognisable within one line and corrosive to the credibility the content was supposed to earn. Without a card direction a frame generator invents a look nobody chose, and a feed where nothing matches is most of what a card was meant to prevent.
Three rules govern this skill:
- It ships a template, never a voice. A captured voice is personal data — one
person's register, derived from their own writing.
VOICE.mdis generated into your project and is gitignored by default, because most repos a skill runs in are public or shared. What ships with the plugin is the shape and the two shipped rule lists. This is the same relationshipmodel-strategyhas todocs/MODEL-STRATEGY.md: the skill writes the file, the file is not the skill. - Never invent a voice. Asked how someone writes, a model will produce a
confident, generic answer. If the user supplies neither samples nor answers, the
positive half of
VOICE.mdstays empty and says so. A plausible voice nobody chose is worse than an admitted gap, because every later draft inherits it silently. - Detect, map, confirm — never impose. Additive only. Inherited from
repo-setupanddesign-setup, because they are the same two problems. If the project already calls itcontent/, the tier iscontent/. Every write is a file that did not exist.
The canon
Used only to fill gaps. An existing path always wins.
| Path | What it holds | Committed? |
|---|---|---|
posts/README.md |
The tier's tense: derived — it cites the record, never a source | yes |
posts/VOICE.md |
How the posts sound | gitignored by default |
posts/VOICE.example.md |
The shape, plus the banned moves and the AI-tells pointer | yes |
posts/CARD.md |
How the frames look | gitignored by default |
posts/CARD.example.md |
The shape | yes |
posts/material/README.md |
The backlog index | yes |
posts/material/assets/ |
Snapshots of a before-state | yes |
posts/cards/ |
Rendered frames | yes |
What ships with it
1 file 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.
- 8d ago First seen · 239 lines · 112 tokens per session scan C 93598422671e
post-setup is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 112 tokens to every session and 3,207 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…