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.
npx agentmods add instructions/dliedke/claudecodeextension/agents-mdgit clone --depth 1 https://github.com/dliedke/ClaudeCodeExtensionWhat 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 | $0.00686 | $0.00686 |
| Opus 5 | $0.00343 | $0.00343 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
ClaudeCodeExtension AGENTS.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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for ClaudeCodeExtension
Build & Test
- Build:
msbuild ClaudeCodeExtension.sln /p:Configuration=Releaseormsbuild ClaudeCodeExtension.sln /p:Configuration=Debug - Tests:
./test.cmdbuildsTests/ClaudeCodeExtension.Tests.csprojand runs it undervstest.console.exe(no VS instance needed) — version/package guards plus unit tests of pure helpers (parsers, formatters, path/session logic).publish.cmdruns it as a gate before releasing (SKIP_TESTS=1bypasses it). - Debug: Press F5 in Visual Studio to launch experimental instance with
/rootsuffix Exp. Anything needing a running VS (terminal embedding, provider round-trip, settings dialog) is only exercised this way.
Code Style
- Language: C# targeting .NET Framework 4.7.2 for Visual Studio 2022 SDK
- File Headers: Every
.csfile must include copyright header with author (Daniel Liedke), copyright year (2026), and proprietary usage notice - Namespace: Use
ClaudeCodeVSfor main controls,ClaudeCodeExtensionfor package class - Partial Classes: Main control is split into specialized partial classes (e.g.,
ClaudeCodeControl.Settings.cs,ClaudeCodeControl.Terminal.cs) - Imports: Use explicit
usingstatements; avoid wildcard imports. Common:System,System.Windows,Microsoft.VisualStudio.Shell - Types: Use C# built-in types (
string,bool,double) over BCL types (String,Boolean,Double) - Naming: PascalCase for public members,
_camelCasewith underscore for private fields, camelCase for local variables - Error Handling: Use try-catch with
Debug.WriteLinefor logging; showMessageBoxfor user-facing errors - Comments: XML doc comments (
///) for public members describing purpose; inline comments for complex logic - Settings: Persist to JSON at
%LocalAppData%\ClaudeCodeExtension\claudecode-settings.jsonusing Newtonsoft.Json - Thread Safety: Use
ThreadHelper.ThrowIfNotOnUIThread()andJoinableTaskFactory.SwitchToMainThreadAsync()for UI thread operations - Resources: Dispose terminal processes and temp directories in
Dispose()pattern; clean up%TEMP%\ClaudeCodeVS\*on startup - Constants: Use
constfor hardcoded strings (e.g.,ConfigurationFileName),static readonlyfor computed values
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.
- 2d ago First seen · 28 lines · 686 tokens per session scan A e2d4c36d0cfc
ClaudeCodeExtension AGENTS.md is an instructions file published in the GitHub repository dliedke/ClaudeCodeExtension (67 stars, last pushed 4d ago), licensed MIT. It adds 686 tokens to every session, about $0.0034 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 2026-08-30.
Other instructions, from other repositories
gortex CLAUDE.md
Claude Code instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).
cursor-mcp-bridge CLAUDE.md
Instructions for JaimeJunr/cursor-mcp-bridge, covering claude.md, what this is, commands, architecture and engines & tiers (multi-cli).
codeseeker CLAUDE.md
Claude Code instructions for jghiringhelli/codeseeker: Smart Claude Code CLI — semantic search, graph analysis, token-optimized code intelligence. Read .claude/index.md before any task. Load .claude/core.md always.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.