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 mtarcure/claude-vibe-squad --skill persuasive-technical-writinggit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/persuasive-technical-writing)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/persuasive-technical-writing"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/persuasive-technical-writing/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/mtarcure/claude-vibe-squad/persuasive-technical-writing"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/persuasive-technical-writing.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 | $0.00069 | $0.01642 |
| Opus 5.5 | $0.00028 | $0.00657 |
| Sonnet 5.5 | $0.00014 | $0.00328 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
persuasive-technical-writing 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persuasive Technical Writing
Turn raw technical findings into human-sounding, high-retention long-form prose. The rules below are ordered by impact against six failure symptoms; each priority names the symptom it fixes, so jump to your problem. Every rule is mechanically checkable: where a rule states a number, that number is the test a reviewer or a later pass runs with a grep or a count.
How to use
Run two passes, never one. Pass 1 builds structure and argument: Priority 2 (cohesion), Priority 3 (section titles), Priority 5 (analogies). Pass 2 is a mechanical prose linter over the countable rules: Priority 1 (cadence and blacklist), Priority 4 (quotes), Priority 6 (bolding and hook). Do not lint before the argument holds, and do not ship before the lint passes.
Priority 1: Human cadence and anti-AI rhythm (fixes "does not sound human")
- Rule 1.1 (Gary Provost burstiness rule): Never write three consecutive sentences of similar length (within ±3 words). In every 200-word block, enforce at least one short punch sentence (<7 words) and at least one rhythmic compound sentence (>25 words).
- Rule 1.2 (hard lexical blacklist): Strictly ban the Kobak et al. excess words. Zero instances permitted. Grep the draft for each token:
delve, tapestry, testament, beacon, pivotal, intricate, realm, underscores, harnessing, multifaceted, interplay, moreover, furthermore, in conclusion, at its core - Rule 1.3 (de-symmetrization): Ban symmetrical parallelism (
not only X, but also Y;from X to Y and beyond). Break formulaic 3-part bullet lists into continuous narrative paragraphs. - Rule 1.4 (Williams character-action rule): Express characters as grammatical subjects and core actions as active verbs. Ban empty openings (
There is,There are,It is important that) and strip nominalizations ending in-tion,-ment,-ance.
Priority 2: Cohesion and information pacing (fixes "hard to stay with")
- Rule 2.1 (Williams given-before-new): The first 6-8 words of every sentence must connect semantically to a concept established in the immediate prior sentence. Place novel, complex, or heavy technical terms strictly at the end of the sentence (the stress position).
- Rule 2.2 (mobile paragraph ceiling): On mobile and X viewports, cap paragraphs at 1-3 sentences (maximum 40-60 words). Never stack two 3-sentence paragraphs; alternate with 1-sentence pivot paragraphs.
- Rule 2.3 (Minto problem-first flow): Introduce technical solutions only after establishing the Situation and Complication. Maintain forward causal momentum; every paragraph must answer the question raised by the preceding one.
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.
- 1mo ago First seen · 66 lines · 69 tokens per session scan A 32ab28e10e25
persuasive-technical-writing is a skill published in the GitHub repository mtarcure/claude-vibe-squad (165 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,642 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-20.
Other skills, from other repositories
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
skill-installer
Install, update, trust, or inspect Codewhale skills from GitHub or local skill folders. Use when the user asks for available skills or wants a community skill installed.