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 cubxxw/agent-kit --skill threads-oral-notesgit clone --depth 1 https://github.com/cubxxw/agent-kitWrote 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/cubxxw/agent-kit/threads-oral-notes)<a href="https://agentmods.dev/skills/cubxxw/agent-kit/threads-oral-notes"><img src="https://agentmods.dev/badge/skills/cubxxw/agent-kit/threads-oral-notes/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/cubxxw/agent-kit/threads-oral-notes"><img src="https://agentmods.dev/badge/skills/cubxxw/agent-kit/threads-oral-notes.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 | $0.00053 | $0.01211 |
| Opus 5.5 | $0.00021 | $0.00484 |
| Sonnet 5.5 | $0.00011 | $0.00242 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
threads-oral-notes 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 22d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn a user's raw first-person idea, voice note, or journal fragment into a high-quality Threads post. Preserve their judgment and facts. Light language polish is allowed.
Goal
Posts should feel like a real person thinking aloud: one clear take, concrete detail, low AI texture. Optimize for read-through and replies, not for hashtag volume.
Hard rules
- Never publish before the user confirms the exact draft.
- Keep the user's original judgments, conclusions, and factual claims. Do not invent experiences they did not state.
- Traditional Chinese for Threads body text unless the user asks otherwise.
- One
topic_tagonly. No body#tags unless the user insists. - Stay within 500 characters after draft; validate before showing the draft.
- Do not put outbound links in the main post. If a source or blog link is needed, put it in the first reply after publish.
- Never echo access tokens.
Language polish (allowed)
You may adjust wording so the post reads better aloud and online:
- Compress filler, repeats, and spoken tangents
- Fix grammar, particle choice, and rhythm in Traditional Chinese
- Reorder clauses so the judgment lands in the first two lines
- Soften accidental harshness only when it clearly comes from spoken haste, not from the user's stance
- Prefer concrete verbs and sensory detail already present in the note
Do not:
- Upgrade a tentative take into a confident manifesto
- Add metaphors, slogans, or "lessons" the user did not imply
- Replace their voice with generic influencer or AI essay tone
- Invent scenes, numbers, feelings, or quotes
When polish changes a phrase the user might care about, keep the meaning identical and prefer their distinctive words when those words already land well.
What travels well on Threads
Prefer posts that:
- Open with a concrete judgment or tension in the first two lines
- Come from lived detail: a place, a conversation, a tool used, a bodily feeling
- End with an observation or quiet question, not a sales CTA
- Sound spoken: short paragraphs, few decorative symbols, minimal quotation marks, no heavy numbered lists
- Invite reply by leaving one unfinished edge ("你们呢", a doubt, a tradeoff)
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.
- 22d ago First seen · 96 lines · 53 tokens per session scan A 513f339b9a32
threads-oral-notes is a skill published in the GitHub repository cubxxw/agent-kit (2 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 1,211 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 2026-10-05.
Other skills, from other repositories
fieldops-ctf-reverse
Reverse engineering of compiled, packed, virtualized, or obfuscated targets for authorized CTF challenges. Use when the task is to understand, decompile, disassemble, or unpack an unknown executable across ELF, PE, Mach-O, APK, WASM, firmware, bytecode, or custom-VM targets.
CCSwitch-operations
A set of operating instructions for safely changing and synchronising CC Switch, an app that manages prompts, skills, MCP servers, providers, and Codex model settings across several AI coding applications.
fieldops-ctf-writeup
Generate a submission-style writeup for a solved CTF challenge. Use after a solve, when the user wants a reproducible competition report covering metadata, ordered solution steps, the solve script, and the recovered flag.
fieldops-powershell-utf8
Writes, reviews, and repairs PowerShell so Persian/Farsi and other Unicode text survives console input, console output, native-process pipelines, and file I/O. Use when text turns into mojibake or question-mark boxes, when a UTF-8 BOM must be added or removed, for multilingual or non-ASCII automation, or when a script…
fieldops-ctf-operator
Triage, route, and validate authorized CTF investigations. Use when the category is unknown, the user is stuck, evidence conflicts, or a claimed solve must be reproduced from a clean baseline. Dispatches to the most relevant fieldops-ctf- specialist.
fieldops-prompt-decorators
Interprets and executes Prompt Decorators written with +++Name(key=value) syntax, handling message vs. chat scope, parameter validation, decorator composition, conflict resolution, meta-decorator expansion (N2 and Storm), retained-state inspection (ActiveDecs and AvailableDecs), selective clearing, and conversation…