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 OutlineDriven/outline-driven-development --skill copywritinggit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/copywriting)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/copywriting"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/copywriting/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/outlinedriven/outline-driven-development/copywriting"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/copywriting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 84 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00052 | $0.07059 |
| Opus 5 | $0.00026 | $0.03529 |
| Sonnet 5 | $0.00010 | $0.01412 |
| Haiku 4.5 | $0.00005 | $0.00706 |
Grade A, and why
copywriting 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 2d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copywriting
Contract
| Field | Bound contract |
|---|---|
| Trigger | Write or fix product or marketing copy, landing pages, UI strings, or brand voice, or remove AI tells (page); design or review a bottom-of-article CTA (cta); write a hook, lede, or accroche for long-form content (hook). |
| Authority | Reversible local. Writes only user-facing copy and brand voice outputs in the working tree; cta and hook modes emit chat output only. Rollback is version control. No remote mutation. |
| Side effect | Creates or edits copy files and brand voice outputs in page mode; cta and hook modes produce conversation only. |
| Done | Page: copy is free of AI-isms, matches the voice chart, and fits the page type. Cta: the full recommendation structure is composed. Hook: the user has selected a hook and its commitments are named. |
Inputs
- Mode selector:
page,cta, orhook. Auto-detect from the ask: a bottom-of-article call-to-action routes tocta; a hook, lede, or accroche for long-form content routes tohook; anything else routes topage. An explicit mode argument overrides auto-detection. - Mode page: copy to fix, or a page type and goal. Select the editing branch when copy exists or the user pasted it; the writing branch when nothing is written yet. For a genuinely ambiguous request ("improve this" with no copy in scope), ask one question, then commit.
- Mode cta: article context, primary objective, audience and relationship, funnel stage, and mechanism preference, collected in the interview step.
- Mode hook: topic, audience, target language (EN, FR, or both), approximate length, and publication venue; an optional existing draft opening, treated as Option 0 and never silently discarded.
- Optional inputs, settled before writing: page purpose, audience, product, traffic source, and any voice file (
VOICE.md,BRAND.md,docs/voice.md). If an input is missing, infer it and name the inference so the user can correct it against real copy.
Procedure
What ships with it
3 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.
- 2d ago Changed · +37 lines · -5 tokens per session 4ebefc511545
- 5d ago First seen · 109 lines · 57 tokens per session scan A 441a90ef3b2e
copywriting is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 52 tokens to every session and 7,059 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 2026-09-03.
Other skills, from other repositories
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.