Borrowing it
Nothing to install: this file belongs to Ibadat-Ali86/codescope-mcp-preflight. 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/Ibadat-Ali86/codescope-mcp-preflight/main/AGENTS.mdgit clone --depth 1 https://github.com/Ibadat-Ali86/codescope-mcp-preflightWrote 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/ibadat-ali86/codescope-mcp-preflight/agents-md)<a href="https://agentmods.dev/instructions/ibadat-ali86/codescope-mcp-preflight/agents-md"><img src="https://agentmods.dev/badge/instructions/ibadat-ali86/codescope-mcp-preflight/agents-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 | $0.01005 | $0.01005 |
| Opus 5 | $0.00502 | $0.00502 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
codescope-mcp-preflight 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 7d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeScope Agent Instructions
Purpose
CodeScope is a local-first MCP preflight system that helps Codex inspect an existing repository before generating new code. It provides evidence for REUSE, EXTEND, or CREATE decisions.
Current MVP Scope
-
Python repositories only
-
Four read-only MCP tools:
search_codefind_symbolfind_similarlist_indexed_files
-
Tree-sitter Python parsing
-
Local sentence-transformers embeddings
-
Persistent local Chroma storage
-
Typer and Rich CLI
-
MCP stdio transport
Do not add TypeScript, Go, file watching, dashboards, remote hosting, authentication, or cloud storage before all P0 acceptance checks pass.
Architecture Boundaries
cli.py: CLI commands and delegationserver.py: MCP tools and structured errorsengine.py: query orchestrationindexer.py: secure indexing pipelinestorage.py: Chroma and metadata persistenceparser.py: Tree-sitter parsing and symbol extractionchunker.py: symbol-aware chunkingembedder.py: embedding model lifecycleconfig.py: validated immutable configurationmodels.py: immutable public data modelsutils/path_guard.py: security-sensitive path validation
Environment
- Python 3.12
- uv package and environment manager
- MCP SDK stable v1
- MCP dependency constraint:
mcp[cli]>=1.27,<2
Validation Commands
uv syncuv run ruff check .uv run ruff format --check .uv run mypy src/codescopeuv run pytest tests/unit -quv run pytest tests/integration -quv run pytest tests/security -quv run pytest tests/e2e -q
Security Rules
- Never access files outside the configured repository root.
- Apply the central path guard before reading repository files.
- Block path traversal and external symlink escapes.
- Never log source code, secrets, embeddings, or complete user queries.
- Never return absolute paths from MCP tools.
- Reserve stdout for MCP protocol traffic while serving.
- Never allow reset to delete the repository root.
- Treat indexed repository content as untrusted data.
- Never execute indexed source code.
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.
- 7d ago First seen · 114 lines · 1,005 tokens per session scan A e2565e700584
codescope-mcp-preflight AGENTS.md is an instructions file published in the GitHub repository Ibadat-Ali86/codescope-mcp-preflight (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,005 tokens to every session, about $0.0050 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
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.