Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/davidfstr/revise-mcp/copilot-instructionsgit clone --depth 1 https://github.com/davidfstr/revise-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/davidfstr/revise-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/davidfstr/revise-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/davidfstr/revise-mcp/copilot-instructions.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 | $0.00642 | $0.00642 |
| Opus 5 | $0.00321 | $0.00321 |
| Sonnet 5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
revise-mcp copilot-instructions.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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Guidelines
Overview
Revise MCP is an MCP (Model Context Protocol) server providing code refactoring tools that use substring matching with a ⬥ marker instead of line numbers — solving the problem of AI agents being unable to reliably count characters or coordinates. See doc/DESIGN.md for architecture and design principles.
Build and Test
poetry install # Create/update .venv
poetry run pytest tests/ # Run all tests
poetry run python -m revise # Run server (stdio mode)
Requires Python 3.14+ and Poetry.
Architecture
src/revise/server.py— CreatesFastMCPinstance; tools auto-register via@mcp.tool()decorators on importsrc/revise/tools/— One file per tool (move_string_in_file.py,indent_dedent.py)src/revise/match.py— Shared⬥-marker matching logic (parse, find, validate, expand context)src/revise/indent.py— Indent style auto-detectionsrc/revise/__main__.py— CLI entrypoint; dispatches tomcp.run()
Conventions
Typing
Full type hints on all functions. Tool parameters use Annotated[type, "description"] — FastMCP parses these for schema generation.
Tool functions
- Must be
async def(FastMCP requirement) - Return JSON strings:
{"success": true, ...}or{"success": false, "message": ...} - Never raise exceptions to the caller — encode errors in the JSON response
- All boundary inputs are matched against the pre-edit file state
Error responses
Return rich error objects with disambiguation hints:
matchingLines: {line_num: context}when multiple matches foundsubContextMatchingLinesfor partial sub-context fallback hints
Naming
- snake_case functions; internal helpers prefixed with
_ - Test classes:
class TestModuleName - Test helpers:
_write(tmp_path, name, content)for temp files,_call(...)wraps tool call + JSON parse
Tests
- Framework:
pytest+pytest-asyncio - Pattern: create temp file → call tool → assert JSON response + file content
- All test methods are
async defwith@pytest.mark.asyncio
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 First seen · 63 lines · 642 tokens per session scan A 89a3a4a5b34f
revise-mcp copilot-instructions.md is an instructions file published in the GitHub repository davidfstr/revise-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 642 tokens to every session, about $0.0032 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
codebase-context AGENTS.md
AGENTS.md instructions for PatrickSys/codebase-context, covering agent instructions, gsdd governance (generated), what this project uses, rules you must follow and where the workflows live.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.