What is TLDR CLAUDE.md?

Maintainer instructions for TLDR, a tool that makes coding-agent responses shorter while retaining useful code, file paths, tool actions, and safety details.

Use them when modifying TLDR prompts, commands, skills, agents, installers, hooks, plugins, documentation assets, or tests.

They explain where the project’s source files live and which files should be edited first, reducing the risk of changing generated or incorrect copies.

TLDR CLAUDE.md — Instructions file for coding agents by 0p9b: Maintainer instructions for TLDR, a tool that makes coding-agent…

Install

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.

agentmods

npx agentmods add instructions/0p9b/tldr/claude-md

Clone the repo

git clone --depth 1 https://github.com/0p9b/TLDR

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/0p9b/tldr/claude-md.svg)](https://agentmods.dev/instructions/0p9b/tldr/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/0p9b/tldr/claude-md"><img src="https://agentmods.dev/badge/instructions/0p9b/tldr/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,004 This file is loaded in full into every session.

When invoked 2,004 The same file — it is already loaded in full.

Security scan B 1 finding. Scan, not verified.

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	$0.02004	$0.02004
Opus 5	$0.01002	$0.01002
Sonnet 5	$0.00401	$0.00401
Haiku 4.5	$0.00200	$0.00200

Measured 5d ago against content hash 946f483af9db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

TLDR CLAUDE.md scanned grade B 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Native (no-npx, self-contained) providers install a fenced always-on TLDR ruleset into the agent's global instruction file plus the full auto-discovered TLDR skill suite (the 8 `OPENCODE_SKILL_DIRS`: `tldr`, `tldr-commit

CLAUDE.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — TLDR maintainer guide

Product

TLDR makes AI coding agents answer in compressed, verdict-first prose while preserving tool use, code, paths, safety, and technical accuracy.

Public repo: https://github.com/0p9b/TLDR

Tagline: Verdict first. Filler never.

Source layout

TLDR/
├── TLDR.md                         # canonical prompt
├── commands/                       # slash-command TOML/Markdown
├── skills/                         # source skills
├── agents/                         # source tldrcrew subagents
├── bin/install.js                  # full multi-agent installer
├── install.sh                      # lightweight prompt-only copier
├── install-full.sh / install.ps1   # full-installer shims
├── src/hooks/                      # Claude hook/statusline stack
├── src/plugins/tldr-opencode/      # opencode native plugin source
├── src/plugins/tldr-pi/            # Pi Coding Agent extension source
├── src/mcp-servers/tldr-shrink/    # optional MCP description compressor
├── docs/assets/                    # mascot/social/favicon assets
└── tests/                          # installer + safety + smoke tests

Edit rules

Edit source first: skills/**, agents/**, src/**, bin/**, commands/**.
Run python3 tests/verify_repo.py before any commit touching skills, agents, hooks, plugins, or installer code.
Do not add legacy package names, legacy hook markers, or legacy skill paths to shipped code/docs.
Historical lineage belongs in docs/legal/ATTRIBUTION.md, docs/legal/THIRD_PARTY_NOTICES.md, or data/**, not in install paths or public commands.

Install paths

Path	Purpose
`bash install.sh`	prompt-only local/global copier
`npx -y github:0p9b/TLDR -- --all`	full multi-agent installer
`bash install-full.sh -- --all`	shell shim to full installer
`pwsh install.ps1 -- --all`	PowerShell shim to full installer
`node bin/install.js --list`	provider matrix

Supported full-installer providers include Claude, Gemini, Codex, Pi Coding Agent, Grok Build CLI, oh-my-pi, Cursor, Windsurf, Cline, Continue, Kilo, Roo, Augment, opencode, OpenClaw, Hermes Agent, Copilot, Aider Desk, Amp, Bob, Crush, Devin, Droid/Factory, ForgeCode, Goose, iFlow, Kiro, Mistral, OpenHands, Qwen, Rovo Dev, Tabnine, Trae, Warp, Replit, Junie, Qoder, and Antigravity (38 total; node bin/install.js --list).

Read the full file on GitHub · 124 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.

5d ago First seen · 124 lines · 2,004 tokens per session scan B 946f483af9db

Subscribe to this mod's changes

TLDR CLAUDE.md is an instructions file published in the GitHub repository 0p9b/TLDR (23 stars, last pushed 12d ago), licensed MIT. It adds 2,004 tokens to every session, about $0.0100 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LLM Prompt Optimization agentic-ai ai-agents gemini prompt-engineering

TLDR CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

CLAUDE.md — TLDR maintainer guide

Product

Source layout

Edit rules

Install paths

What this file has done since we first saw it

Other instructions, from other repositories

shreyas-skills copilot-instructions.md

DuDuClaw CLAUDE.md

shreyas-skills CLAUDE.md

shreyas-skills AGENTS.md

avoid-ai-writing CLAUDE.md

prompt-improver AGENTS.md