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 charlie947/agent-harness-starter --skill post-writer-examplegit clone --depth 1 https://github.com/charlie947/agent-harness-starterWrote 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/charlie947/agent-harness-starter/post-writer-example)<a href="https://agentmods.dev/skills/charlie947/agent-harness-starter/post-writer-example"><img src="https://agentmods.dev/badge/skills/charlie947/agent-harness-starter/post-writer-example/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/charlie947/agent-harness-starter/post-writer-example"><img src="https://agentmods.dev/badge/skills/charlie947/agent-harness-starter/post-writer-example.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 | $0.00076 | $0.00434 |
| Opus 5 | $0.00038 | $0.00217 |
| Sonnet 5 | $0.00015 | $0.00087 |
| Haiku 4.5 | $0.00008 | $0.00043 |
Grade A, and why
post-writer-example 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 10d 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.
What it actually says
Post Writer (example)
Drafts a LinkedIn post in the user's voice from a topic or rough idea.
This is a starter template. Replace every [placeholder] with your own files and rules, then save and fire it from any chat.
Step 1 — Gather inputs
Ask the user:
- "What's the topic?"
- "Any specific angle or hook in mind, or should I propose one?"
- "Standard length, or short/long?"
Step 2 — Pull voice references
Read:
[path/to/your/voice-file.md][path/to/past-best-posts.md][path/to/banned-words.md]
If you have a brand kit, also read [path/to/brand-kit.md].
Step 3 — Draft
Write the post following these rules:
- [Your sentence length rule]
- [Your hook rule]
- [Your CTA rule]
- [Your formatting conventions — line breaks, bullets, emojis]
Step 4 — Self-critique
Score the draft 0-100 against:
- Hook strength (30 pts)
- Voice match (30 pts)
- Mechanism specificity (20 pts)
- CTA fit (20 pts)
If under 90, rewrite and re-score. Never show below 90.
Step 5 — Deliver
Show the user the post. Ask:
Want me to: (a) publish to Notion drafts, (b) save to file, or (c) iterate?
Non-negotiables
- Never invent stats. Verify every number against a source.
- Never use the banned words list.
- British/US English consistent with the user's global rule.
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.
- 10d ago First seen · 61 lines · 76 tokens per session scan A 1d64aab1287f
post-writer-example is a skill published in the GitHub repository charlie947/agent-harness-starter (22 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 434 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 2026-08-30.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…