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 isvlasov/rageatc-oss --skill persuadinggit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote 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/isvlasov/rageatc-oss/persuading)<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.
<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>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 | $0.00057 | $0.02083 |
| Opus 5 | $0.00028 | $0.01042 |
| Sonnet 5 | $0.00011 | $0.00417 |
| Haiku 4.5 | $0.00006 | $0.00208 |
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.
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?
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.
- 9d ago First seen · 117 lines · 57 tokens per session scan A 0867771fc0b9
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.
Other skills, from other repositories
design-method
Use when starting any design task — resolves register, sets the 3 dials, locks Gate 0, and routes to the right move and target skill.
design-webapp
Use when building or extending a dashboard, SaaS screen, or any authenticated app surface — use design-web instead for a marketing site.
design-web
Use when building or revising a marketing/landing/campaign page, register brand locked at Gate 0 — use design-webapp for app screens instead.
fusecore
Use when creating modules, understanding FuseCore structure, or implementing features in a FuseCore modular-monolith Laravel project.
laravel-architecture
Use when structuring a Laravel project, creating services/repositories/actions, implementing dependency injection, or organizing code layers.
laravel-auth
Use when implementing user authentication, API tokens, social login, or authorization in Laravel 13.