What is tacit CLAUDE.md?

Project-specific instructions for Claude Code when working on the tacit repository. They describe the technologies, folder layout, commands, and build checks used by the project.

Following development guidelines, finding the right commands, understanding the project structure, and checking whether a build succeeds.

They give the coding agent the project’s working rules, reducing incorrect commands and changes that do not fit the repository.

How sangmin7648/tacit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sangmin7648/tacit. 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/sangmin7648/tacit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sangmin7648/tacit

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/sangmin7648/tacit/claude-md/github.svg)](https://agentmods.dev/instructions/sangmin7648/tacit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sangmin7648/tacit/claude-md"><img src="https://agentmods.dev/badge/instructions/sangmin7648/tacit/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sangmin7648/tacit/claude-md"><img src="https://agentmods.dev/badge/instructions/sangmin7648/tacit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,513 This file is loaded in full into every session.

When invoked 1,513 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	$0.01513	$0.01513
Opus 5.5	$0.00605	$0.00605
Sonnet 5.5	$0.00303	$0.00303
Haiku 4.5	$0.00151	$0.00151

Measured 28d ago against content hash 83ad10bc0c63, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tacit 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 28d 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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tacit

tacit turns spoken words into a searchable local knowledge base: it listens to the microphone, transcribes on-device, classifies each transcript with an LLM, and stores it as a Markdown file that AI agents can search.

The Go module, Makefile, and all code live in tacit/; run every make and go command from there. The repo root holds docs/ and what GitHub or users reach by URL: README.md, install.sh, .github/, LICENSE.

Read docs/index.md first. It lists every document and what it covers. The code is the source of truth; docs/ explains the why and the shape at a high level.

Code layout

The folders say what tacit does; keep it that way. Rationale: 0011.

tacit/app/<binary>/                    cli, desktop: parse input, show output, decide nothing
tacit/packaging/<os>/                  turn the binaries into what a user installs
tacit/core/workflows/<verb>/           what an app can ask for: listen, control, onboard, browse, configure
tacit/core/internal/components/<-er>/  the parts workflows combine

Names. A workflow folder is a verb; a component folder is an -er/-or noun (transcriber, note-manager). The Go package is the folder name without hyphens.
Direction. app → workflow → component. Workflows never import each other; components never import each other, except setting-manager and the audio format in mic-recorder. internal/ makes the compiler reject an app importing a component.
Types. When an app needs a component's type, the workflow re-exports it as an alias (type Note = notemanager.KnowledgeEntry).
Linking. Go links whole packages. Code the desktop app imports must not share a package with CGo audio code; split the package instead.
Belongings. Third-party code, bundled binaries and testdata/ live inside the folder that uses them. Operating-system differences go in file suffixes (_darwin.go) inside the component.

Build rules

Read the full file on GitHub · 103 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.

28d ago Changed · +19 lines · +354 tokens per session 83ad10bc0c63
28d ago Changed · +25 lines · +584 tokens per session 9b6771f5c2e6
2mo ago First seen · 59 lines · 575 tokens per session scan A e62c786a0b1d

Subscribe to this mod's changes

tacit CLAUDE.md is an instructions file published in the GitHub repository sangmin7648/tacit (11 stars, last pushed 11d ago), licensed MIT. It adds 1,513 tokens to every session, about $0.0061 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 2026-08-31.

autodetection harness harness-engineering local-ai ondevice-ai vad

tacit CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tacit CLAUDE.mdsangmin7648/tacit	Instructions file	11	11d ago	MIT	A	1,513	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

tacit: Instructions file for Claude Code