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 Soul-Brews-Studio/arra-oracle-skills-cli --skill oracle-title-forgegit clone --depth 1 https://github.com/Soul-Brews-Studio/arra-oracle-skills-cliWrote 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/soul-brews-studio/arra-oracle-skills-cli/oracle-title-forge)<a href="https://agentmods.dev/skills/soul-brews-studio/arra-oracle-skills-cli/oracle-title-forge"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/oracle-title-forge/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/soul-brews-studio/arra-oracle-skills-cli/oracle-title-forge"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/oracle-title-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00217 | $0.02083 |
| Opus 5 | $0.00109 | $0.01042 |
| Sonnet 5 | $0.00043 | $0.00417 |
| Haiku 4.5 | $0.00022 | $0.00208 |
Grade A, and why
oracle-title-forge 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 11d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/oracle-title-forge — forge a title that has life, honestly
Born 2026-07-09 turning the dead "ผ่าไส้ Discord Channel ของ Claude Code" into "Claude Code Channel ปะทะ Hermes Gateway — สองสถาปัตยกรรมที่ทำให้ AI คุยบน Discord ได้…" The lesson: a great title is grown from understanding what the thing IS, not shuffled from words.
Why the method works (read this first)
A dead title fails one specific way: it has clarity without intrigue. "ผ่าไส้ X" tells you the topic and nothing else — no tension, no question, no stake. Every principle below exists to add intrigue without lying. The magic isn't wordsmithing; it's that each step forces you to understand the material more deeply, and the title falls out of that understanding.
The method — 7 moves
1. Describe before you name
Never start by brainstorming words. First write what each thing IS — once vividly, once in plain technical terms. The title grows from this. (For the Discord book, writing "the plugin is a stdio bridge tied to a session's lifecycle; Hermes is an always-on daemon" is what revealed the contest.)
2. Find the real tension — and check it's not forged
If it's a comparison/VS, run a skeptic pass: is the contest real or clickbait? Two things at different layers can't fight on features. Reframe the tension at the honest layer — philosophy, fit, tradeoff — not a fake feature-fight. A title promising a showdown the book can't deliver is a lie. (Discord book: they're transport vs runtime — so the contest is "two philosophies of presence," which is true, not "which codes better," which is false.)
3. Prism the candidates — 3-5 lenses
Look at each candidate from angles a single view misses. Useful lenses for titles:
- 🏪 Bookshelf browser — does the spine make someone pick it up?
- 💀 Honest skeptic — does the title over-promise? name only one side of a two-sided story?
- 🧑💻 Dev-ear — would a developer actually say this phrase? Kill words devs don't use ("ให้ AI พูด" → "AI คุยบน Discord"; "ต่อ AI เข้ากับ Discord" → clunky; "data เข้าทางไหน" ✓ real).
- ✍️ Thai editor — cadence, clean noun phrases, cut stray connectors (ด้วย/ต่อ...เข้ากับ).
- 🎯 Precision — does the subtitle name the real axes, not vague adjectives?
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.
- 11d ago First seen · 139 lines · 217 tokens per session scan A 9d63d61445b1
oracle-title-forge is a skill published in the GitHub repository Soul-Brews-Studio/arra-oracle-skills-cli (121 stars, last pushed 5d ago), licensed MIT. It adds 217 tokens to every session and 2,083 once invoked, about $0.0011 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…