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 phazonoverload/devadvokit --skill repurpose-talkgit clone --depth 1 https://github.com/phazonoverload/devadvokitWrote 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/phazonoverload/devadvokit/repurpose-talk)<a href="https://agentmods.dev/skills/phazonoverload/devadvokit/repurpose-talk"><img src="https://agentmods.dev/badge/skills/phazonoverload/devadvokit/repurpose-talk/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/phazonoverload/devadvokit/repurpose-talk"><img src="https://agentmods.dev/badge/skills/phazonoverload/devadvokit/repurpose-talk.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 | $0.00060 | $0.00966 |
| Opus 5.5 | $0.00024 | $0.00386 |
| Sonnet 5.5 | $0.00012 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
repurpose-talk 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 2mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before doing anything else:
- Check if
~/.devadvokit.mdexists. - If it does, read it silently and use it throughout this skill.
- If it does not, stop and tell the user: "I need your DevRel context before I can run this skill. Please run /setup-devadvokit first."
What NOT to Do
This skill produces outlines, angles, and frameworks — not full drafts. Specifically:
- No full blog posts — outlines only. Full drafts are scope creep and end up generic without heavy editing.
- No video scripts — that's a different skill.
- No SEO metadata — separate concern, different skill.
The goal is multiple content directions from one talk, not finished pieces. Editing produces the final versions.
Q&A
Ask these questions one at a time. Wait for each answer before asking the next.
-
What's the talk title and abstract? (Paste or type — this is required. If you only have a title and need help with an abstract, say so and I'll help you draft one.)
-
Do you have a script, speaker notes, or transcript? Paste it here or provide a file path. This allows me to ground outputs in your actual content rather than infering from the abstract alone. If you only have the abstract, I can still work with that.
-
Who's the target audience for the repurposed content, and what's their familiarity level? (Beginner / practitioner / expert — this affects depth and terminology)
-
What tone should the repurposed content have? (Technical and depth-focused? Conversational and approachable? Thought leadership and industry perspective?)
-
What conference or event was this presented at, and when? (This gives context and provides "as I presented at X" framing for the repurposed content)
Quality Gates (if transcript/notes provided)
If transcript or notes were provided, process them before generating outputs:
-
Pull 2–3 pull quotes — direct lines that work as standalone social copy. Memorable, quotable, out-of-context friendly.
-
Flag demo or live content — anything that won't translate to written formats. Note what needs adaptation or removal.
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.
- 2mo ago First seen · 98 lines · 60 tokens per session scan A 4b28072318b9
repurpose-talk is a skill published in the GitHub repository phazonoverload/devadvokit (16 stars, last pushed 7mo ago), licensed MIT. It adds 60 tokens to every session and 966 once invoked, about $0.0002 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 2026-08-30.
repurpose-talk compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repurpose-talkphazonoverload/devadvokit | Skill | 16 | 7mo ago | MIT | A | 60 | Claude Code, Codex |
| 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 |