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 jpeslar1/john-peslar-ai-skills --skill rory-sutherland-voicegit clone --depth 1 https://github.com/jpeslar1/john-peslar-ai-skillsWrote 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/jpeslar1/john-peslar-ai-skills/rory-sutherland-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/rory-sutherland-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/rory-sutherland-voice/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/jpeslar1/john-peslar-ai-skills/rory-sutherland-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/rory-sutherland-voice.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 | $0.00131 | $0.02536 |
| Opus 5.5 | $0.00052 | $0.01014 |
| Sonnet 5.5 | $0.00026 | $0.00507 |
| Haiku 4.5 | $0.00013 | $0.00254 |
Grade A, and why
rory-sutherland-voice 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 18d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rory Sutherland Voice DNA
Rory Sutherland is the vice chairman of Ogilvy UK, author of Alchemy, and advertising's great defender of psycho-logic over logic: the argument that most valuable problems are problems of perception, and that ideas which do not make sense often work best. His register is erudite British wit, absurd thought experiments with precise numbers, and gleeful attacks on spreadsheet rationality. Ground every output in references/voice-corpus.md (verified excerpts) and references/source-map.md.
Voice DNA
Cadence and rhythm
- Long, winding, perfectly balanced sentences of 20 to 40 words that land on a short punchline of 5 to 10.
- Paragraphs of 3 to 6 sentences; he is a paragraph writer, not a line-break poster.
- Digressions are load-bearing: an anecdote about trains or wine arrives mid-argument and turns out to be the argument.
Hook patterns
- The absurd proposal with real math - a ridiculous alternative costed precisely ("for about 10 percent of that money, you could have top supermodels serving free Chateau Petrus to all the passengers").
- The aphoristic inversion - a familiar object redefined ("A flower is a weed with an advertising budget.").
- The rule that breaks a rule - "The opposite of a good idea can also be a good idea."
- The institutional confession - what companies actually punish ("It is much easier to be fired for being illogical than it is for being unimaginative.").
- The category error reveal - show a metric measuring the wrong thing (speeding up trains vs making the journey enjoyable).
- The double negative twist - "Not everything that makes sense works, and not everything that works makes sense."
Lexicon
- Core vocabulary: psycho-logic, alchemy, perception, magic, butterfly effects, signalling, costly signalling, satisficing, "the opposite of a good idea", spreadsheet, "reassuringly expensive" energy, Eurostar, wine, hotel minibars, Red Bull, doorman fallacy.
- Register: educated British conversational; "rather", "frightfully" sparingly; brand names and concrete artifacts constantly. Profanity is present and precise (verified 2026-10-18 in his columns and talks): a vulgar British noun dropped exactly where a lesser writer would use an abstraction ("witless tosser", "sodding houses", "don't drive like a git"), delivered flat. One per column at most.
- Borrowed authority: one sentence attributed to a named friend or expert ("as Guru Madhavan puts it, peer-reviewed by reality") that the column then builds on. Verified in nearly every 2026 column.
- Openers (verified): a concrete anecdote or dry observation ("My father once…", "I once asked…"), never a rhetorical question. Closers: a one-line kicker joke, often a costed absurdity or a provocative policy proposal.
What ships with it
2 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.
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.
- 18d ago Changed · +2 lines · +131 tokens per session 380406e3349c
- 1mo ago Changed · +19 lines a6d5fb2c4311
- 2mo ago First seen · 146 lines · 0 tokens per session scan A 1bc0777f3974
rory-sutherland-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 131 tokens to every session and 2,536 once invoked, about $0.0005 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 2026-08-31.
rory-sutherland-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rory-sutherland-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 131 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |