persuading

persuading is a skill for Claude Code from isvlasov/rageatc-oss. It costs 57 tokens per session (2,083 once invoked), scanned A, original, MIT.

A writing method for showing the genuine value of a subject to a specific audience. It focuses on understanding the subject first, then framing and expressing its value clearly.

In plain words
What is it for?
Use it for LinkedIn posts, pitches, cover letters, proposals, case studies, and other positioning work.
Why use it?
It helps when good work is hard for others to recognize because the message assumes too much knowledge or does not connect with the audience’s needs.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the rageatc-core-oss plugin — 24 skills, 6 agents shipped together

Good fit Use it for LinkedIn posts, pitches, cover letters, proposals, case studies, and other positioning work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/isvlasov/rageatc-oss/persuading
Install

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.

Any agent
npx skills add isvlasov/rageatc-oss --skill persuading
Clone the repo
git clone --depth 1 https://github.com/isvlasov/rageatc-oss

Made for: Claude Code.

Or install rageatc-core-oss, the plugin that ships this one along with the rest of its 24 skills, 6 agents.

Wrote 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.

agentmods badge for persuading

README.md
[![agentmods](https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/persuading/github.svg)](https://agentmods.dev/skills/isvlasov/rageatc-oss/persuading)
Your own site
<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/persuading"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/persuading/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.

agentmods 80×15 button for persuading

Your own site · 80×15
<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/persuading"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/persuading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,083 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.02083
Opus 5 $0.00028 $0.01042
Sonnet 5 $0.00011 $0.00417
Haiku 4.5 $0.00006 $0.00208

Measured 9d ago against content hash 0867771fc0b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

persuading 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 9d 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.

plugins/rageatc-core-oss/skills/persuading/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persuading

A specialisation of communicating-in-writing for making genuine value visible. Medium freedom: follow extract → frame → express in order — skipping extraction and going straight to expression is the most common cause of value communication that fails — but adapt each phase's depth to the mode and context.

Why value communication fails

Three systematic miscalibrations. They are calibration problems, not character flaws; the methodology corrects them structurally:

  • Curse of knowledge — experts skip context, assume shared vocabulary, and abstract where they should concretise, mistaking their own fluency for the subject's simplicity.
  • Visibility gap — people underinvest in making their value visible, then overestimate how apparent it already is. Excellent work does not advertise itself.
  • Empathy gap — self-promoters overestimate positive reactions and underestimate negative ones, producing either silence or miscalibrated noise.

Modes

  • Preparation — dialogue with a user preparing a pitch or positioning decision; gather subject, audience, goal, and context through conversation. Output: a positioning strategy — the value, the frame, talking points.
  • Review — diagnosing existing content. Audit it against the three phases before revising: which does it fail, and why? Fix root causes, not surface symptoms. Audience and goal must still be established.
  • Agent — producing persuasive content autonomously from a brief; subject, audience, goal, and context must be provided upfront. Output: the finished artefact.

Phase 1 — Extract

Excavate the genuine value before attempting to communicate it.

Identify the real job being done. People hire products and people to get a job done, not for features and credentials:

  • Functional — what practical task does this solve?
  • Emotional — how does the audience want to feel after this? (confident, relieved, respected, safe)
  • Social — how do they want to be perceived by others for this decision?

Read the full file on GitHub · 117 lines

Changes

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.

  1. 9d ago First seen · 117 lines · 57 tokens per session scan A 0867771fc0b9

Subscribe to this mod's changes

persuading is a skill published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,083 once invoked, about $0.0003 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 2026-08-31.