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/clawdotnet/sharpclawcode/agents-mdgit clone --depth 1 https://github.com/clawdotnet/SharpClawCodeWhat 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 | $0.01692 | $0.01692 |
| Opus 5 | $0.00846 | $0.00846 |
| Sonnet 5 | $0.00338 | $0.00338 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
SharpClawCode 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 yesterday.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Identity
SharpClaw Code is a C#-native coding-agent harness inspired by the current Rust claw-code surface.
Primary stack:
- .NET 10
- C# 13
- Microsoft Agent Framework
System.CommandLineSpectre.ConsoleSystem.Text.JsonMicrosoft.Extensions.Hosting- idiomatic Microsoft dependency injection
This repository should grow into a production-grade, cross-platform agent runtime with strong Windows compatibility. Favor concrete, maintainable architecture over framework-heavy indirection.
Current Repository State
The repository may begin sparse or empty. Before implementing anything:
- Inspect the current solution and folder layout.
- Align new work to what already exists unless the user explicitly asks for restructuring.
- If the intended architecture is not present yet, create the smallest real vertical slice that establishes it cleanly.
Do not scaffold broad placeholder trees with no executable value.
Non-Negotiable Engineering Rules
- Target
.NET 10andC# 13. - Prefer clear, explicit, strongly typed code over clever abstractions.
- Use
async/awaitend-to-end anywhere I/O or external process work exists. - Use records for immutable contracts where appropriate.
- Use interfaces for infrastructure seams and runtime orchestration seams.
- Avoid unnecessary repository patterns and avoid overengineered CQRS.
- Keep domain and protocol contracts dependency-light.
- Use
System.Text.Json, neverNewtonsoft.Json. - Use
Microsoft.Extensions.Loggingabstractions for logging. - Prefer file-scoped namespaces.
- Favor small, testable classes with focused responsibilities.
- Preserve machine-readable state and JSON output support across major features.
- Route dangerous shell execution or file mutation through an explicit permission policy layer.
- Model long-running or lifecycle-managed subsystems explicitly and use hosted services where appropriate.
- Build for cross-platform support, with strong Windows behavior and path/process compatibility.
- Do not hardcode secrets, API keys, tokens, or machine-specific paths.
- Add concise XML docs for all public APIs and major internal services.
- Add
TODOcomments only when paired with a concrete reason.
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.
- yesterday First seen · 163 lines · 1,692 tokens per session scan A 23650eb6d2e9
SharpClawCode AGENTS.md is an instructions file published in the GitHub repository clawdotnet/SharpClawCode (85 stars, last pushed 1mo ago), licensed MIT. It adds 1,692 tokens to every session, about $0.0085 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
nina AGENTS.md
Instructions for isbeorn/nina, covering agents.md, scope, documentation boundary, repository knowledge and code style and formatting.
Sighthound AGENTS.md
Instructions for Corgea/Sighthound, covering claude, commands, python / django test naming and agent skill.
amp-acp AGENTS.md
Instructions for tao12345666333/amp-acp, covering agents.md, commands, architecture and code style.
roamcode AGENTS.md
Instructions for burakgon/roamcode, covering repository instructions for coding agents, public-repository safety, stable release and ota contract, releasing a stable version and ota changes.
Fluence.Wpf AGENTS.md
Instructions for sintaxasn/Fluence.Wpf, covering fluence.wpf - developer handbook, 1. project overview, solution layout, clr namespaces and 2. coding standards.
E2E Harness Self-Fixing Protocol
Rules for working with the Sir Thaddeus E2E test harness. Governs how to diagnose, fix, and verify failures without gaming the scoring system.