Borrowing it
Nothing to install: this file belongs to mhaviv/pr-narrator-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/mhaviv/pr-narrator-mcp/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/mhaviv/pr-narrator-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/mhaviv/pr-narrator-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/mhaviv/pr-narrator-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mhaviv/pr-narrator-mcp/copilot-instructions/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/mhaviv/pr-narrator-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mhaviv/pr-narrator-mcp/copilot-instructions.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 | $0.01020 | $0.01020 |
| Opus 5 | $0.00510 | $0.00510 |
| Sonnet 5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
pr-narrator-mcp copilot-instructions.md scanned grade A with 1 finding 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 8d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Flag any use of `child_process`, `exec`, `execSync`, or `spawn` — this project uses `simple-git` exclusively How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository-Wide Code Review Instructions
Security (Highest Priority)
- Verify
validateRepoPath()is called before anysimple-gitoperation on user-supplied paths - Check for path traversal vulnerabilities in any function accepting file or repo paths
- Verify all user-supplied regex patterns are validated via
validateRegexPattern()before use - Ensure no hardcoded secrets, API keys, or credentials anywhere in the codebase
- Check that diff and output sizes are bounded — look for
MAX_DIFF_SIZEusage or equivalent limits - Flag any use of
child_process,exec,execSync, orspawn— this project usessimple-gitexclusively - Reject any code that writes to the git repository — all operations must be read-only
- Verify that null byte injection is prevented in path handling
Git Operation Safety
- All git operations must go through
simple-gitwith a validated path fromvalidateRepoPath() - Never execute arbitrary git commands via shell
- Always handle git operation failures gracefully with try/catch — return
nullor empty defaults - Verify that new git operations do not modify the repository (no commits, checkouts, or resets)
- Ensure
createGit(validatedPath)is used, not rawsimpleGit()calls
MCP Protocol Compliance
- Tool handlers must never throw exceptions — return
{ success: false, errors: [...] } - Tool definitions must have
name(snake_case),description, andinputSchema(JSON Schema object) - Input schemas use Zod with
.optional()and.describe()for all parameters - Config is always the second parameter to handlers, never imported directly in tool files
- Tool results are serialized as
{ type: "text", text: JSON.stringify(result, null, 2) } - New tools must be registered in
src/index.ts: imports,toolsarray, andCallToolRequestSchemaswitch
Error Handling
- Functions must not throw — return result objects with
errors: string[]andsuccess: boolean - Use
error instanceof Error ? error.message : String(error)for safe error extraction in catch blocks - Git failures return
nullor empty defaults, never crash the server - Zod parse errors are caught and reported as tool errors, not re-thrown
- The
index.tshandler wraps all calls in try/catch as a safety net — tools should still handle their own errors
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.
- 8d ago First seen · 86 lines · 1,020 tokens per session scan A ec35f3de68a3
pr-narrator-mcp copilot-instructions.md is an instructions file published in the GitHub repository mhaviv/pr-narrator-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 1,020 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.