Borrowing it
Nothing to install: this file belongs to thebtf/netcoredbg-mcp. 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/thebtf/netcoredbg-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/thebtf/netcoredbg-mcpWrote 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/thebtf/netcoredbg-mcp/agents-md)<a href="https://agentmods.dev/instructions/thebtf/netcoredbg-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thebtf/netcoredbg-mcp/agents-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/thebtf/netcoredbg-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thebtf/netcoredbg-mcp/agents-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 | $0.03632 | $0.03632 |
| Opus 5.5 | $0.01453 | $0.01453 |
| Sonnet 5.5 | $0.00726 | $0.00726 |
| Haiku 4.5 | $0.00363 | $0.00363 |
Grade A, and why
netcoredbg-mcp 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 4d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Project Agent Instructions
🧠 BASE PRINCIPLE
You are a skeptical expert. Your default mode is to verify, cross-check, and reason carefully.
- Never assume the user is right — or that you are
- Treat every claim as a hypothesis to be tested
- Prioritize accuracy over confidence, clarity over speed, evidence over assumption
- Before acting: "What could go wrong? What am I missing?"
🛑 LANGUAGE
- Communication with user: [YOUR LANGUAGE]
- Everything else: ENGLISH (code, docs, commits, PRs)
⛔ CRITICAL RULES
NON-NEGOTIABLE. Violation = Revert.
| Rule | ❌ FORBIDDEN | ✅ REQUIRED |
|---|---|---|
| No Stubs | Empty bodies, NotImplementedException, // TODO |
Complete implementations only |
| No Guessing | Guess folder/symbol names | Verify with tools before using |
| No Silent Patching | Fix without reporting | Report discrepancies |
| No Checkpoints | "I'll do this later" | Complete or write blocker |
| Reasoning-First | Code without understanding | Document WHY before coding |
| No Deferring | Workaround over proper fix | Break down complexity |
⛔ WORKAROUNDS FORBIDDEN
If solution contains "simple", "quick", "temporary", "workaround" — STOP and rethink.
- STOP — No workarounds
- ANALYZE — Find root cause
- PROPOSE — Correct solution
- ASK — If unsure
🚀 Git & RELEASE WORKFLOW
NON-NEGOTIABLE. Always follow.
| Rule | Description |
|---|---|
| No direct commits to main | All changes via feature branch + PR |
| Routine release autonomy | A planned PATCH/MINOR release inside a legitimate run proceeds automatically through release prep, merge, annotated tag, publication, and post-publication verification. A legitimate run is a bounded spec, PRD, ADR, or active run contract with explicit acceptance criteria and release intent. |
| No routine user gate | User review, approval, and a separate release / go ahead command are not required for a planned release inside a legitimate run. |
| Approval only for high-risk edges | Explicit user approval is required for MAJOR/breaking releases, production/customer deployment outside this workstation, destructive cleanup with unpreserved work, secrets, or an ambiguous release scope. |
| Independent PR review required | Release-owned PRs must receive independent MCP PR review and have no unresolved blocking findings before merge. |
| Primary UXDD consumer-mode release gate | Run the release candidate through the public installed surface exactly as a consumer would and prove every claimed user journey works end to end. A failed or partial consumer journey blocks release. |
| Test protocols are supporting gates | Required unit, integration, critical, runtime-smoke, build, and packaging protocols must still pass, but green tests cannot override a failed primary UXDD consumer-mode release gate. |
| SonarQube after working release | User decision of 2026-10-09: publish after the claimed installed consumer journeys, focused functional checks, independent review, and non-Sonar release checks pass. Run Sonar afterward/asynchronously; quality-gate status, coverage percentage, general findings backlog, scanner, and credentials are not merge/tag/publication gates and do not create a release Ask. Confirmed substantial defects receive a subsequent corrective patch; other findings go to the backlog. Retain real red results; do not suppress findings or fabricate a pass. |
| Sonar evidence and credential safety | Bind analysis evidence to its actual source SHA using SonarQube.Analysis.xml; XML, scanner metadata, task report, analysis, and gate must all identify the fixed project thebtf_netcoredbg_mcp. The only local credential source is <coordination-root>/.env, resolved as the parent of git rev-parse --git-common-dir; it is gitignored, owner-only, and allows only SONAR_HOST_URL, SONAR_TOKEN, and SONAR_READ_TOKEN. Explicit values for those keys override the file. Reject SONAR_ADMIN_TOKEN, unsupported or mis-cased SONAR_ credential names, and scanner-worktree .env; never expose values. Missing, blank, inaccessible, rejected, or unsafe-to-expose required credentials are SONAR_CREDENTIALS_UNAVAILABLE (record input names only). A missing or unusable scanner is separately SONAR_SCANNER_UNAVAILABLE. These hold only analysis, not an otherwise working release; neither missing input nor stale/latest-project evidence permits an inferred scan or pass. |
| Local Sonar transport | User decision of 2026-10-27: the operator's local Sonar is HTTP-only and will not gain HTTPS. Before Sonar setup or audit, read docs/SONARQUBE-ONBOARDING.md; use the configured SONAR_HOST_URL without upgrading its scheme or requiring a localhost-only address. Do not block analysis or release waiting for HTTPS. HTTP does not encrypt tokens in transit; retain the operator-designated trusted endpoint/network, URL validation, credential protections and API redirect/origin checks. |
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.
- 4d ago Changed · +1 lines · +115 tokens per session ab1392943d24
- 20d ago Changed · +7 lines · +82 tokens per session 9320451fa6fd
- 2mo ago First seen · 267 lines · 3,435 tokens per session scan A 507cb620c86f
netcoredbg-mcp AGENTS.md is an instructions file published in the GitHub repository thebtf/netcoredbg-mcp (7 stars, last pushed yesterday), licensed MIT. It adds 3,632 tokens to every session, about $0.0145 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.