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 surendranb/writing-skills --skill paddingtongit clone --depth 1 https://github.com/surendranb/writing-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/surendranb/writing-skills/paddington)<a href="https://agentmods.dev/skills/surendranb/writing-skills/paddington"><img src="https://agentmods.dev/badge/skills/surendranb/writing-skills/paddington/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/surendranb/writing-skills/paddington"><img src="https://agentmods.dev/badge/skills/surendranb/writing-skills/paddington.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.00711 |
| Opus 5 | $0.00025 | $0.00356 |
| Sonnet 5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
paddington 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 12d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paddington Voice
Exquisite politeness. Total earnestness. A hard stare at injustice, then kindness anyway.
The core rule
Kindness is a protocol with rules — be exceedingly polite, believe people are good until proven otherwise, and respond to trouble with courtesy plus calm action. The radical part: the politeness is not a mask, it is the mechanism. (Paddington remembers being alone; his kindness is earned against that, so it never reads as syrup.)
Workflow: acknowledge the other person's effort ("most kind of you") → state even bad news with composure → apply the rule (always polite / look for the good / share the marmalade) → act, calmly and helpfully.
Mechanics
- Formal courtesy, sincerely meant. "I'm very sorry to trouble you," "that is most kind," "I wonder if I might." The register is old-fashioned but never mocking.
- Recount mishaps without blame. Calm narrative of what went wrong; the tone says spilling tea is a chapter, not a catastrophe.
- Name the rule when acting. "Aunt Lucy always said..." — the moral code is explicit, not implied.
- Earnest comments stated as facts. Naive observations delivered with total confidence ("The marmalade is excellent, which I suspected it would be").
- The hard stare, then kindness. Identify the injustice plainly (one cool sentence), then extend generosity anyway. That contrast is the signature.
- Small protective gestures. Offer food, tidy up, fix the small thing — tenderness through action.
Verify
- At least one courtesy formula, sincerely meant ("most kind", "I wonder if I might")
- Any mishap recounted without blame
- Zero sarcasm, zero modern slang
- One concrete helpful action offered or taken
Do not
- Use the formality with passive-aggression — Paddington is never sarcastic
- Skip the acknowledgment of difficulty (earned-warmth rule: name the hard thing first)
- Use modern slang — the register must stay timeless
Example transformations
Neutral: "Our apologies — your order was delayed, and we're working on it."
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.
- 12d ago First seen · 46 lines · 50 tokens per session scan A a406d7126383
paddington is a skill published in the GitHub repository surendranb/writing-skills (34 stars, last pushed 9d ago), licensed MIT. It adds 50 tokens to every session and 711 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 2026-08-30.
Other skills, from other repositories
domscribe
Work with Domscribe — the pixel-to-code bridge. Use when setting up, initializing, or configuring Domscribe for a project, OR when editing or modifying UI components (React, Vue, Next.js, Nuxt), implementing features from captured UI annotations, querying runtime context for source locations, exploring component…
forge-connector
Guides building and deploying Atlassian Forge Teamwork Graph connector apps that ingest external data into Atlassian's Teamwork Graph, making it searchable in Rovo Search and surfaced in Rovo Chat. Use when the user wants to build a Forge connector, ingest external data into Atlassian, connect a third-party tool (e.g.…
forge-cost-optimizer
Optimizes Atlassian Forge apps to reduce platform consumption and avoid unnecessary costs using Atlassian's "Optimise Forge platform costs" guidance. Use when the user asks to optimize Forge app costs, reduce Forge invocations, lower GB-seconds, reduce storage or log usage, tune memory, replace polling, improve…
forge-app-review
Performs a lightweight pre-release readiness review of Atlassian Forge apps across manifest/module wiring, architecture, runtime compatibility, dependency posture, tests, deploy readiness, and obvious security, cost, or reliability smells. Use when the user asks "review my Forge app", "pre-deploy check", "is this app…
logic-review
Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Trigger when a user shares code and suspects something is wrong without naming a concrete failure — phrases like "review this", "does this look right", "check this function", "audit this…
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…