Borrowing it
Nothing to install: this file belongs to baizhiyuan/finding-unknowns-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/baizhiyuan/finding-unknowns-skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/baizhiyuan/finding-unknowns-skillWrote 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/instructions/baizhiyuan/finding-unknowns-skill/claude-md)<a href="https://agentmods.dev/instructions/baizhiyuan/finding-unknowns-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/baizhiyuan/finding-unknowns-skill/claude-md/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/instructions/baizhiyuan/finding-unknowns-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/baizhiyuan/finding-unknowns-skill/claude-md.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 | $0.00454 | $0.00454 |
| Opus 5 | $0.00227 | $0.00227 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
finding-unknowns-skill 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 9d 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.
What it actually says
finding-unknowns (passive drop-in)
Drop this file into a project root (or paste into your own CLAUDE.md) if you want the
finding-unknowns habits without installing the skill or plugin. It's a lighter, always-on
nudge; the full skill (with copy-paste prompts and Cartographer mode) lives in
skills/finding-unknowns/SKILL.md.
The map is not the territory. The bottleneck on long-horizon work is clarifying your unknowns. Before building something ambiguous or unfamiliar, spend cheap words to find them — it's always cheaper than rework.
When a task is fuzzy or unfamiliar, first locate the unknown
- Unknown Unknowns (blind spots) → run a blind-spot pass: landmines, hidden context, what "good" looks like, and the questions an expert would ask. Do not implement yet.
- Unknown Knowns ("I'll know it when I see it") → brainstorm several throwaway directions or point at reference code, so tacit taste becomes explicit.
- Known Unknowns (nameable gaps) → interview one question at a time, architecture first; or write a plan that leads with the decisions most likely to change.
- Known Knowns → just write them down before they drift.
During and after
- Mid-build, keep implementation notes: log any deviation and the conservative choice.
- Before merge, quiz yourself on what actually changed. Comprehension is the gate.
Guardrails
- Discovery ends at understanding — don't slide into implementation.
- Prioritize architecture-changing unknowns over trivia.
- "No significant unknowns here" is a valid, valuable result.
Distilled from Thariq Shihipar's essay "A Field Guide to Fable: Finding Your Unknowns" (@trq212). Community project; not affiliated with or endorsed by Anthropic.
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.
- 9d ago First seen · 38 lines · 454 tokens per session scan A 0b286882d663
finding-unknowns-skill CLAUDE.md is an instructions file published in the GitHub repository baizhiyuan/finding-unknowns-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 454 tokens to every session, about $0.0023 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.
Other instructions, from other repositories
runtm copilot-instructions.md
Copilot instructions for runtm-ai/runtm, covering runtm tool instructions, critical rules, structure, adding endpoints and app/api/v1/myendpoint.py.
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.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.