What is unknowns CLAUDE.md?

Repository instructions for maintaining the unknowns Claude Code plugin and its portable agent skills. They describe the folder layout, naming rules, and documentation requirements.

Use them when creating, updating, documenting, or reviewing skills in the unknowns repository.

They give contributors shared rules for adding or changing skills without making the plugin structure inconsistent.

How hiendinhngoc/unknowns configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hiendinhngoc/unknowns. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/hiendinhngoc/unknowns/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/hiendinhngoc/unknowns

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hiendinhngoc/unknowns/claude-md.svg)](https://agentmods.dev/instructions/hiendinhngoc/unknowns/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/hiendinhngoc/unknowns/claude-md"><img src="https://agentmods.dev/badge/instructions/hiendinhngoc/unknowns/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 667 This file is loaded in full into every session.

When invoked 667 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00667	$0.00667
Opus 5	$0.00333	$0.00333
Sonnet 5	$0.00133	$0.00133
Haiku 4.5	$0.00067	$0.00067

Measured 8d ago against content hash ac202098bd33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

unknowns CLAUDE.md 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 8d 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.

CLAUDE.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This repo publishes the unknowns Claude Code plugin and portable Agent Skills.

Repo shape

Skills live flat under skills/<name>/SKILL.md:

blindspot — read-only pre-implementation risk scan
verify-ref — comprehension gate before porting/reference-copying
mock — disposable prototype for unresolved UX/behavior
log-deviation — record plan-vs-code deviations during implementation
merge-quiz — pre-merge quiz on risky diff areas
unknowns — router/orchestrator; keep routing logic here, technique logic in the target skill

Keep every skill referenced in the top-level README.md skills table. Plugin package metadata lives in .claude-plugin/; do not add per-skill entries there unless Claude's plugin format starts requiring them.

Skill conventions

Each skill is one directory containing SKILL.md and agents/openai.yaml with:

---
name: <kebab-name>
description: <trigger phrases + when to use it>
version: 1.0.0
author: Hien Dinh
license: MIT
---

# Title

Rules:

name must match the directory.
description drives model invocation; include user phrases people will actually say.
Put hard constraints near the top with <HARD-RULE> or <HARD-GATE>.
End with an explicit output format.
If a skill mentions Claude-specific tools (Artifact tool, AskUserQuestion, Skill tool, Glob/Grep/Read), include the portable fallback in the same skill.
Keep skills portable: no repo-specific paths, no hidden Claude-only requirement unless a fallback is documented.
Keep SKILL.md under 500 lines and add resources only when progressive disclosure or deterministic tooling earns them.
Keep agents/openai.yaml display metadata and $skill-name default prompt aligned with SKILL.md.

Adding or changing skills

Update skills/<name>/SKILL.md.
Update the top-level README.md skills table and examples if the user-facing behavior changes.
If unknowns should route to the skill, update skills/unknowns/SKILL.md.
Run:

Read the full file on GitHub · 76 lines

Changes

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.

8d ago First seen · 76 lines · 667 tokens per session scan A ac202098bd33

Subscribe to this mod's changes

unknowns CLAUDE.md is an instructions file published in the GitHub repository hiendinhngoc/unknowns (9 stars, last pushed 1mo ago), licensed MIT. It adds 667 tokens to every session, about $0.0033 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 2026-08-31.

Claude Code agent-skills ai-agents codex-cli hermes-agent opencode

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

unknowns: Instructions file for Claude Code