actual-mcp-server: Instructions file for GitHub Copilot

.github/instructions/tool-files.instructions.md

actual-mcp-server tool-files.instructions.md is an instructions file for GitHub Copilot from agigante80/actual-mcp-server. It costs 789 tokens per session, scanned A, original, MIT.

Project instructions for MCP tool files, which define the callable actions exposed by this server. They describe file names, input validation, shared fields such as dates and account IDs, and adapter usage.

In plain words
What is it for?
Use them when creating or editing files in src/tools/, defining schemas, validating arguments, and calling the server's adapter methods correctly.
Why use it?
They prevent inconsistent tool interfaces, invalid data handling, and deadlocks caused by opening nested API sessions.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions CLAUDE.md.

This is agigante80/actual-mcp-server's own configuration. It tells GitHub Copilot how to work on actual-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything actual-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to agigante80/actual-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/agigante80/actual-mcp-server/main/.github/instructions/tool-files.instructions.md
Clone the repo
git clone --depth 1 https://github.com/agigante80/actual-mcp-server

Made for: GitHub Copilot.

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 actual-mcp-server tool-files.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/agigante80/actual-mcp-server/tool-files.svg)](https://agentmods.dev/instructions/agigante80/actual-mcp-server/tool-files)
Your own site
<a href="https://agentmods.dev/instructions/agigante80/actual-mcp-server/tool-files"><img src="https://agentmods.dev/badge/instructions/agigante80/actual-mcp-server/tool-files.svg" alt="Measured on agentmods" height="20"></a>
Per session 789 This file is loaded in full into every session.
When invoked 789 The same file — it is already loaded in full.
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 $0.00789 $0.00789
Opus 5 $0.00394 $0.00394
Sonnet 5 $0.00158 $0.00158
Haiku 4.5 $0.00079 $0.00079

Measured 8d ago against content hash 5e3d67511a73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

actual-mcp-server tool-files.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 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.

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.

.github/instructions/tool-files.instructions.md · 31 lines

What it actually says

Rules for MCP tool files (src/tools/*.ts)

  • Tool name MUST follow actual_{domain}_{action} snake_case convention
  • File name MUST match the tool name (e.g. accounts_create.ts for actual_accounts_create)
  • InputSchema MUST use z.object({...}) from Zod
  • Use types from CommonSchemas in src/lib/schemas/common.ts for shared fields:
    • Dates → CommonSchemas.date (validates YYYY-MM-DD)
    • Account UUIDs → CommonSchemas.accountId
    • Amounts → CommonSchemas.amountCents (integer cents, never decimal dollars)
  • The call function MUST InputSchema.parse(args) before any other logic
  • NEVER wrap an adapter.* call in a session of your own. adapter.* methods already open one, and the API mutex (withApiLock in actual-adapter.ts) is NOT reentrant, so nesting deadlocks. What you observe is a ~30s stall then Actual API operation timed out after 30000ms (ACTUAL_OP_TIMEOUT_MS), because #270 bounds each operation inside the lock and that timeout is what breaks the deadlock. Read that error as a probable nesting bug, not a slow server.
  • Default to calling adapter.* methods. Do NOT reach for @actual-app/api just to avoid a wrapper.
  • Importing @actual-app/api directly is correct in one case: when you are already INSIDE a single adapter session callback and need more than one operation in that one cycle. Then use the raw functions, because calling back through adapter.* from in there is the nesting deadlock above. Exactly ONE tool file does this today (see CLAUDE.md):
    • budget_updates_batch.ts: raw calls inside adapter.batchBudgetUpdates(...), a batch of pure writes
  • A read-then-write guard belongs in the ADAPTER, not the tool (#371, #376). Four tool files used to hold one inside their own withWriteSession; all four were migrated. A guard in the tool costs retry on the reads, bypasses the observability call site, and leaves the matching adapter.* method reachable and UNGUARDED, which is how adapter.deleteRule sat callerless while silently failing to delete a schedule-owned rule. The single-cycle property does not require the raw api: queueWriteOperation holds the lock for its whole body
  • When you move a guard into the adapter, fix its test's seam too. Stubbing adapter.withWriteSession as a pass-through stubs away the guard itself. Use _setSkipApiInitForTests(true) with the RAW api functions stubbed BEFORE the adapter import (it destructures them at module load), and assert the cycle count with _getWriteQueueBatchCountForTests()
  • Error messages must be actionable: include entity type, ID, and a suggested next tool
  • After creating a tool file, you MUST:
    1. Export it from src/tools/index.ts
    2. Add the name to IMPLEMENTED_TOOLS in src/actualToolsManager.ts
    3. Run npm run build first (verify-tools reads from dist/, not src/)
    4. Run npm run verify-tools to confirm registration
  • To check uncovered Actual API surface before implementing: npm run check:coverage (prints every @actual-app/api method against the current tool list; read-only, safe to run)

On conflict, CLAUDE.md is authoritative over this file. It carries the same rules with fuller rationale.

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. 8d ago First seen · 31 lines · 789 tokens per session scan A 5e3d67511a73

Subscribe to this mod's changes

actual-mcp-server tool-files.instructions.md is an instructions file published in the GitHub repository agigante80/actual-mcp-server (50 stars, last pushed yesterday), licensed MIT. It adds 789 tokens to every session, about $0.0039 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 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens