Borrowing it
Nothing to install: this file belongs to KarpelesLab/tpl. 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/KarpelesLab/tpl/master/CLAUDE.mdgit clone --depth 1 https://github.com/KarpelesLab/tplWrote 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/karpeleslab/tpl/claude-md)<a href="https://agentmods.dev/instructions/karpeleslab/tpl/claude-md"><img src="https://agentmods.dev/badge/instructions/karpeleslab/tpl/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/karpeleslab/tpl/claude-md"><img src="https://agentmods.dev/badge/instructions/karpeleslab/tpl/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 | $0.00352 | $0.00352 |
| Opus 5.5 | $0.00141 | $0.00141 |
| Sonnet 5.5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
tpl 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 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.
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
TPL-GO Developer Guide
Build Commands
make- Format and build projectmake deps- Get all dependenciesmake test- Run all tests
Test Commands
go test -v ./...- Run all tests verboselygo test -v -run=TestName- Run a specific test by name
Code Style
- Use
goimportsfor formatting (run viamake) - Follow standard Go formatting conventions
- Group imports: standard library first, then third-party
- Use PascalCase for exported types/methods, camelCase for variables
- Add comments for public API and complex logic
- Place related functionality in logically named files
Error Handling
- Use custom
Errortype with detailed context - Include error wrapping with
Unwrap()method - Return errors with proper context information (line, position)
Testing
- Write table-driven tests with clear input/output expectations
- Use package
tpl_testfor external testing perspective - Include detailed error messages (expected vs. actual)
- Test every exported function and error case
Dependencies
- Minimum Go version: 1.23.0
- External dependencies managed through go modules
Modernization Notes
- Use
errors.Is()anderrors.As()for error checking - Replace
interface{}withanytype alias - Replace type assertions with type switches where appropriate
- Use generics for type-safe operations
- Implement context cancellation handling for long operations
- Add proper docstring comments for exported functions and types
- Use log/slog for structured logging
- Add linting and static analysis tools
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 · 43 lines · 352 tokens per session scan A c0361d659357
tpl CLAUDE.md is an instructions file published in the GitHub repository KarpelesLab/tpl (4 stars, last pushed 9mo ago), licensed MIT. It adds 352 tokens to every session, about $0.0014 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.
tpl CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tpl CLAUDE.mdKarpelesLab/tpl | Instructions file | 4 | 9mo ago | MIT | A | 352 | 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 |