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/alebgl77/claude-inc/post-writernpx skills add alebgl77/claude-inc --skill post-writergit clone --depth 1 https://github.com/alebgl77/claude-incWrote 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/alebgl77/claude-inc/post-writer)<a href="https://agentmods.dev/skills/alebgl77/claude-inc/post-writer"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/post-writer.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 | $0.00101 | $0.00910 |
| Opus 5 | $0.00051 | $0.00455 |
| Sonnet 5 | $0.00020 | $0.00182 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
post-writer 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 6d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post Writer — Ghostwriter
"Write LinkedIn posts"
When to use
- Turning a win, launch, lesson, or opinion into a LinkedIn or X post.
- "Write a LinkedIn post about our migration off Kubernetes."
- "Turn this blog post into an X post that isn't just a summary."
- "Draft my new-role announcement" / "announce our funding round".
- Rescuing a stiff draft: "make this sound like a person wrote it."
Workflow
- Extract the one idea. Decide what the reader should think, feel, or do after reading. One post carries one idea — park the extras as future posts and say so.
- Load
voice-profile.mdif it exists. Its signature phrases, sentence lengths, punctuation quirks, and vocabulary do/don't override generic style everywhere. - Apply platform physics:
- LinkedIn: only the first 2–3 lines show before "...see more", so the hook must survive the fold; 900–1,300 characters is the sweet spot; breaks are free.
- X: 280 characters and the hook is the whole post; thread only if every tweet stands alone.
- Write the hook first. Draft 5–10 candidates across proven patterns — specific number, contrarian, mistake, transformation, curiosity gap — and promote the strongest to line one.
- Build the body on one spine:
- Story: context → tension → resolution → lesson.
- Insight: claim → evidence → implication. Keep paragraphs to 1–2 lines. Whitespace is the pacing; never a wall of text.
- Close soft: a question worth answering, an invitation, or a plain "follow for more on " — never "thoughts?" or "agree?".
- Produce three full variants of the same idea: story-led, contrarian-led, list-led.
- Self-edit: delete the first sentence if the post works without it (it usually does), cut adverbs, read aloud for cadence, then run the quality bar.
Output format
## Post: <topic> — <platform>
### Variant A — Story
<full post text, formatted exactly as it should be pasted>
### Variant B — Contrarian
<full post text>
### Variant C — List
<full post text>
---
Recommended: <A | B | C> — <one-line reason>
Character counts: A <n> | B <n> | C <n> (limit: <platform rule>)
Voice profile: applied | not found — generic voice used
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.
- 6d ago First seen · 84 lines · 101 tokens per session scan A 50ccb6cc7854
post-writer is a skill published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed 3d ago), licensed MIT. It adds 101 tokens to every session and 910 once invoked, about $0.0005 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
mcp-lark
Based on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.
checklist
Activate when: user says 'let's make sure we don't skip anything', 'we need a pre-flight', 'build me a checklist for X', 'we keep missing steps in our deployment / close / launch', 'Gawande / Pronovost / checklist manifesto'. Do NOT activate when: the task is simple and one-off with no recurrence; the user is asking…
deep-work
Activate when: user says 'I can never find time for focused work', 'I feel busy but produce nothing', 'I keep getting interrupted', 'I want to protect my focus time', 'flow state', 'deliberate practice', 'Cal Newport', or asks how to make progress on hard cognitive work (research, writing, engineering, strategy). Do…
dichotomy-of-control
Activate when: user says "I can't stop worrying about something I can't control," "I'm anxious about how this will turn out," "I keep replaying what went wrong," "I need them to change," "this uncertainty is paralyzing me," or is processing a setback, preparing for a high-stakes unknown outcome, or stuck in…
intrinsic-drive
Activate when: user says 'I've lost motivation', 'I'm burning out', 'the excitement is gone', 'I keep starting things but can't sustain them', 'I'm going through the motions', 'I don't know what drives me anymore', or describes a flat feeling after achieving a major goal. Do NOT activate when: person shows signs of…
knowing-and-doing-as-one
Activate when: user says 'I know I should but I haven't', a team is stuck in analysis paralysis going in circles, you need to assess whether someone actually learned from a past experience, a strategy or lessons-learned doc has produced no operational change, or an organization keeps repeating the same mistake. Do NOT…