Borrowing it
Nothing to install: this file belongs to starless0912/tabless. 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/starless0912/tabless/main/CLAUDE.mdgit clone --depth 1 https://github.com/starless0912/tablessWrote 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/starless0912/tabless/claude-md)<a href="https://agentmods.dev/instructions/starless0912/tabless/claude-md"><img src="https://agentmods.dev/badge/instructions/starless0912/tabless/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/starless0912/tabless/claude-md"><img src="https://agentmods.dev/badge/instructions/starless0912/tabless/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 | $0.00821 | $0.00821 |
| Opus 5.5 | $0.00328 | $0.00328 |
| Sonnet 5.5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
tabless CLAUDE.md scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://127.0.0.1:6181/api/reload How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tabless — notes for coding agents
A local shelf and reader for HTML that coding agents produce. README.md says
what it is for users; this file is what you need to work on it.
Before changing anything
Read CONTRIBUTING.md first. It lists seven design constraints that are not
up for negotiation, and docs/design-notes.md records the failure behind
each one. Both exist because this codebase's hard parts are decisions, not
algorithms — the code is simple and the reasons are not.
The short version, so you recognise when you are about to cross one:
- One reader window, ever. Projects are tabs.
- No process management. A
liveentry whose service is down opens blank, on purpose. - Copies, never references.
- No required third-party dependencies (
pyyamlis optional and must degrade silently). - Loopback only.
- Types stay an open set; nothing in the reader may key off a specific type name.
- Starring lifts an entry out of its group rather than duplicating it.
Layout
src/tabless/config.py |
paths and limits. Read them as config.HOME, never from config import HOME — reconfigure() has to be able to reach you |
src/tabless/core.py |
storage, index, dependency closure, version folding |
src/tabless/projects.py |
project inference and colours |
src/tabless/server.py |
the local service, window reuse, page dressing |
src/tabless/cli.py · client.py |
commands, and talking to the service |
src/tabless/reader.html |
the whole front end, one file |
src/tabless/locales/*.json |
every user-facing string, shared by CLI and reader |
tests/ |
one case per historical bug; docstrings say what broke |
Working on it
pip install -e .
python -m unittest discover -s tests -v
ruff check .
# Never develop against a real library
export TABLESS_HOME=/tmp/tabless-dev TABLESS_PORT=6181
tabless demo
tabless server # foreground, watch it
# reader.html or locales/*.json changed? No restart needed:
curl -X POST http://127.0.0.1:6181/api/reload
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.
- 2mo ago First seen · 72 lines · 821 tokens per session scan A 2fc6c332b0a1
tabless CLAUDE.md is an instructions file published in the GitHub repository starless0912/tabless (2 stars, last pushed 3mo ago), licensed MIT. It adds 821 tokens to every session, about $0.0033 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.