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/xe/agent-plugins/xe-writing-stylenpx skills add Xe/agent-plugins --skill xe-writing-stylegit clone --depth 1 https://github.com/Xe/agent-pluginsWrote 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/xe/agent-plugins/xe-writing-style)<a href="https://agentmods.dev/skills/xe/agent-plugins/xe-writing-style"><img src="https://agentmods.dev/badge/skills/xe/agent-plugins/xe-writing-style.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 | $0.00063 | $0.02765 |
| Opus 5 | $0.00032 | $0.01383 |
| Sonnet 5 | $0.00013 | $0.00553 |
| Haiku 4.5 | $0.00006 | $0.00277 |
Grade A, and why
xe-writing-style 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 3d 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.
This is a copy
88% identical to xe-writing-style — 70 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xe Iaso Blog Post Writer
Transform messy notes into blog posts that sound like Xe Iaso. Read
references/voice-tone.md for detailed voice characteristics. Read 2-3 random
example posts from assets/ to calibrate tone. Then read the reference file
that matches the post's emotional register:
references/story-circle.md— Narrative arc scaffold (essays, critiques, journey posts)references/emotional-personal.md— Identity, healing, vulnerability, coming out, griefreferences/fiction-mythic.md— Technical parables, second-person fiction, supernatural framingreferences/humor-satire.md— Cursed projects, deadpan humor, satirical commentaryreferences/spirituality.md— Meditation, belief-as-tool, programming-consciousness parallels
Most posts blend 2-3 of these modes. Read whichever apply.
What's Load-Bearing
The structural arc and an unbroken register decide whether a post lands; the
signature devices (dialogue, warning boxes, friend-reaction lists) are garnish.
A post that runs its full arc with zero devices reads as a Xe post —
assets/objgit.mdx uses no character dialogue and is the strongest example in
this collection. A post with Xe diction but no architecture does not. Spend
effort on structure, voice consistency, and evidence before any ornament.
Hard Rules
Non-negotiable constraints:
- Successive paragraphs must not start with the same letter. If paragraph N
starts with "T", paragraph N+1 must start with a different letter. Rewrite
sentence openings as needed. Character dialogue blocks (
<Conv>) do not count as paragraphs for this rule. - Write for peers, not beginners. Assume professional-level technical context.
- No corporate or marketing tone. No "leverage", "synergy", "empower", "streamline", "harness", "unlock". Write like a human talking to another human.
- Admit uncertainty. "I think", "I suspect", "I'm not sure" when genuinely uncertain.
- Show tradeoffs, on the page. Never present a solution without its costs, and argue the costs where the claims are — don't defer them to a footnote or another site. The strongest form is a confession: one embarrassing, self-inflicted failure ("It was completely dead in production.") buys more credibility than any disclaimer.
- Context before implementation. Explain why something matters before showing how.
- One narrator. Narrative beats belong to a single first-person voice; "we" appears only in genuinely collective engineering statements. No customer-logo dumps or "You could be next!" closes.
- Numbers carry the argument. Quantify the failure the claim rests on
("over 8,500
GetObjectcalls before I killed it"), not just the effort of building. Every "many", "significant", or "often" becomes a real number or gets cut.
What ships with it
14 files 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.
- assets/anything-message-queue.mdx 31 KB
- assets/gpt-oss-for-agents.mdx 24 KB
- assets/markdownlang.mdx 12 KB
- assets/objgit.mdx 22 KB
- assets/parallel-universes.mdx 28 KB
- assets/rolling-ladder-behind-us.mdx 32 KB
- assets/squandered-holy-grail.mdx 31 KB
- assets/who-assistant-serve.mdx 26 KB
- references/emotional-personal.md 4.3 KB
- references/fiction-mythic.md 4.3 KB
- references/humor-satire.md 6.0 KB
- references/spirituality.md 5.0 KB
- references/story-circle.md 10 KB
- references/voice-tone.md 4.5 KB
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.
- 3d ago First seen · 293 lines · 63 tokens per session scan A d66bcb61b32b
xe-writing-style is a skill published in the GitHub repository Xe/agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 2,765 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to xe-writing-style, differing in 70 lines, and is treated as a copy.
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…