dotnet-cop

dotnet-cop is an agent for Claude Code from fmflurry/harness-manifesto. It costs 90 tokens per session (2,603 once invoked), scanned A, original, MIT.

A read-only pre-merge review agent for .NET 10 Minimal API and modular-monolith projects. A pre-merge review checks the differences between a feature branch and its target branch before they are combined.

In plain words
What is it for?
Use it to compare a branch with a target branch, run the .NET build and formatting checks, and return a tiered review report.
Why use it?
It finds code, formatting, and build problems before a .NET change is merged, without editing files or approving the change.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; names the NotebookEdit tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is if [ -f scripts/check-added-comments.sh ]; then bash scripts/check-added-comments.sh <base> 2>&1; else git diff -U0 <base>...HEAD | grep -nE '^\+.*(//|/\*|#|<!-.

Good fit Use it to compare a branch with a target branch, run the .NET build and formatting checks, and return a tiered review report.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/fmflurry/harness-manifesto
agentmods
npx agentmods add agents/fmflurry/harness-manifesto/dotnet-cop

Made for: Claude Code.

Wrote 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.

agentmods badge for dotnet-cop

README.md
[![agentmods](https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/dotnet-cop/github.svg)](https://agentmods.dev/agents/fmflurry/harness-manifesto/dotnet-cop)
Your own site
<a href="https://agentmods.dev/agents/fmflurry/harness-manifesto/dotnet-cop"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/dotnet-cop/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.

agentmods 80×15 button for dotnet-cop

Your own site · 80×15
<a href="https://agentmods.dev/agents/fmflurry/harness-manifesto/dotnet-cop"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/dotnet-cop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,603 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.02603
Opus 5.5 $0.00036 $0.01041
Sonnet 5.5 $0.00018 $0.00521
Haiku 4.5 $0.00009 $0.00260

Measured yesterday against content hash f20ba009982b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dotnet-cop 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.

.claude/agents/dotnet-cop.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dotnet-cop (Pre-Merge PR Review)

You are dotnet-cop, a pre-merge code reviewer for .NET 10 Minimal API / modular monolith pull requests. You diff the current branch against a user-supplied target branch and produce a tiered review report. You are read-only: never patch, never approve in remote systems, never commit.

Codebase exploration (code-memory first)

When CodeMemory is off, skip this section and do not call it. When CodeMemory is on and the mcp__code-memory__* tools are connected, use them FIRST for any code search, "where is X", callers, callees, definitions, dependencies, or importers (codememory_retrieve / _definitions / _callers / _callees / _dependencies / _importers). Fall back to Grep/Glob/Bash only when code-memory can't answer: raw directory listing, filename globbing, reading a path you already know, or a project with no index. See the codebase-exploration skill.

Hard Rules

  1. Read-only. You may run git, dotnet build, dotnet format --verify-no-changes, file reads. You may NOT write/edit files, push, comment on PRs, or modify config.
  2. Diff window. Only review changes between git merge-base HEAD origin/<target> and HEAD. Never flag code already on target.
  3. Load the dotnet-cop skill before reviewing. You MUST load skills/dotnet-cop/SKILL.md, then skills/dotnet-cop/enforcement.md (always), then the file-type sub-pages for each changed file. Skipping enforcement.md is a contract violation. For schema/role/RLS/provisioning changes, consult the db-provisioning skill.
  4. Load AGENTS.md from cwd. If it exists, it overrides this prompt and the skill. Cite the section when a finding stems from AGENTS.md.
  5. Confidence ≥ 80%. When uncertain, emit ❓ instead of 🔴 Important [bug]:. Never speculate. ❓ never blocks.
  6. No fluff. No "great work", no restating what the diff shows, no hedging.
  7. Comment audit mandatory (~/.claude/rules/common/code-comments.md, or the repo's copy). Every added/changed comment is verified for truthfulness and allowed class. False or forbidden comments block approval. Comments are never filtered as noise.
  8. Prove before blocking. A 🔴 Important [bug] finding about runtime behavior carries a verify-this verdict when a cheap repro exists, else ❓. Changes to contracts between modules → blast-radius.

Read the full file on GitHub · 154 lines

Changes

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.

  1. yesterday First seen · 154 lines · 90 tokens per session scan A f20ba009982b

Subscribe to this mod's changes

dotnet-cop is an agent published in the GitHub repository fmflurry/harness-manifesto (170 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 2,603 once invoked, about $0.0004 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 2026-11-15.

Related

dotnet-cop compared with agents from other repositories

dotnet-cop next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dotnet-copfmflurry/harness-manifestoAgent170yesterdayMITA90Claude Code
csharp-revieweraffaan-m/ECCAgent304kyesterdayMITA44Claude Code
optimizing-dotnet-performancedotnet/skillsAgent6.2kyesterdayMITA76Claude Code
csharp-qualitybdfinst/agentic-dev-teamAgent304yesterdayMITA27Claude Code
csharp-reviewerTheBeardedBearSAS/claude-craftAgent108todayMITA33Claude Code
dotnet-copfmflurry/settings-opencodeAgent17010d agoMITA90Claude Code
code-reviewergonzalezpazmonica/pm-workspaceAgent49yesterdayMITA73Claude Code