Borrowing it
Nothing to install: this file belongs to amusleh-spotware-com/terse-sharp. 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/amusleh-spotware-com/terse-sharp/main/CLAUDE.mdgit clone --depth 1 https://github.com/amusleh-spotware-com/terse-sharpWrote 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/amusleh-spotware-com/terse-sharp/claude-md)<a href="https://agentmods.dev/instructions/amusleh-spotware-com/terse-sharp/claude-md"><img src="https://agentmods.dev/badge/instructions/amusleh-spotware-com/terse-sharp/claude-md.svg" alt="Measured on agentmods" 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 | $0.17613 | $0.17613 |
| Opus 5 | $0.08807 | $0.08807 |
| Sonnet 5 | $0.03523 | $0.03523 |
| Haiku 4.5 | $0.01761 | $0.01761 |
Grade A, and why
terse-sharp 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 3d 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 — 881 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
TerseSharp is a Roslyn-powered MCP server shipped as the .NET global tool terse (package id
TerseSharp, assembly name terse). It gives a coding agent semantic navigation, editing and
refactoring of a C# solution so it never has to Read/Grep/line-Edit a .cs file.
Prime directive, stated in the README and used to settle design arguments: save tokens, increase speed. A tool that does not beat the built-in it replaces does not ship, and a tool without an E2E test is not done.
🚫 HARD GATE — develop TerseSharp with TerseSharp
Every read, search, edit, refactor, build and test of this repository goes through the installed
terse MCP server: get_file_outline / get_symbol_source instead of Read, search_symbols /
find_usages instead of Grep, find_files instead of Glob, replace_symbol_body /
replace_symbol / add_member instead of Edit, read_text / edit_text / write_text for
.md, .csproj, .slnx and .json, build and run_tests instead of shelling out to dotnet,
and changed_files / diff_symbols / diff_text instead of Bash: git status / git diff,
history instead of git log / git show --stat and read_text ref= / get_file_outline ref=
instead of git show <ref>:<path> — so only git blame and index/history mutation (git add,
git commit, git tag, git push) stay on Bash.
This is not style. This repo is the one place where the server is driven by the agent that also maintains it, so every session is the product's own usability test. Friction you route around with a built-in is a defect you never see: the fallback is silent, it feels faster in the moment, and it is exactly the failure mode measured in competing servers (agents that cannot find or trust a tool fall back to the shell and spend more tokens than with no MCP at all).
Dropping to a built-in or to Bash is allowed only when:
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.
- 3d ago Changed · +6 lines · +167 tokens per session 2cbceadebbf2
- 8d ago First seen · 875 lines · 17,446 tokens per session scan A 32991d80f226
terse-sharp CLAUDE.md is an instructions file published in the GitHub repository amusleh-spotware-com/terse-sharp (2 stars, last pushed 3d ago), licensed MIT. It adds 17,613 tokens to every session, about $0.0881 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 2026-08-31.
Other instructions, from other repositories
plan-forge graphql.instructions.md
GraphQL patterns for .NET — Hot Chocolate, code-first schema, DataLoaders, authorization, multi-tenant resolvers.
plan-forge api-patterns.instructions.md
API patterns for .NET — REST conventions, ProblemDetails, pagination, versioning, error responses.
plan-forge errorhandling.instructions.md
Error handling patterns — Exception hierarchy, ProblemDetails responses, error boundaries, global exception middleware.
plan-forge dapr.instructions.md
Dapr patterns for .NET — building blocks, component config, sidecar architecture, multi-tenant isolation, workflows, state management, secrets.
plan-forge blazor-fluent-ui.instructions.md
Blazor Server + Microsoft Fluent UI patterns — component layering, state, lifecycle, accessibility. Auto-loads when editing .razor / .razor.cs files.
plan-forge landing-zone.instructions.md
Azure Landing Zone baselines — identity, network, policy, management, security, tagging, subscription organization.