autotask-mcp: Instructions file for Claude Code

CLAUDE.md

autotask-mcp CLAUDE.md is an instructions file for Claude Code from WYRE-AI/autotask-mcp. It costs 842 tokens per session, scanned A, original, Apache-2.0.

Project instructions and recorded lessons for autotask-mcp, a task-management server using the Task Master command-line tool. They describe known code locations, routing behavior, and TypeScript details.

In plain words
What is it for?
Use them when changing autotask-mcp, especially when adding or checking tools, updating intent routing, or working with its TypeScript result types.
Why use it?
They help an agent avoid implementing tools that already exist and account for known gaps, such as mismatched tool categories or plural entity names.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is WYRE-AI/autotask-mcp's own configuration. It tells Claude Code how to work on autotask-mcp 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 autotask-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to WYRE-AI/autotask-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.

Copy the file
curl -O https://raw.githubusercontent.com/WYRE-AI/autotask-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/WYRE-AI/autotask-mcp

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 autotask-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wyre-ai/autotask-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/wyre-ai/autotask-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/wyre-ai/autotask-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wyre-ai/autotask-mcp/claude-md/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 autotask-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wyre-ai/autotask-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wyre-ai/autotask-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 842 This file is loaded in full into every session.
When invoked 842 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 $0.00842 $0.00842
Opus 5 $0.00421 $0.00421
Sonnet 5 $0.00168 $0.00168
Haiku 4.5 $0.00084 $0.00084

Measured yesterday against content hash a50cf45879cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

autotask-mcp CLAUDE.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 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.md · 26 lines

How it starts

The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.

autotask-mcp

Task management: Task Master (task-master CLI; config in .taskmaster/). Workflow defaults (commits, changelog, memory) come from the global ~/.claude/CLAUDE.md.

Learnings

Learnings - 2026-08-10

  • Issue asks can be stale: #237 claimed "no Contracts tools" but search/create/update already existed (added after the issue was filed). Always scope against src/handlers/tool.definitions.ts before implementing "missing" tools.
  • TOOL_CATEGORIES in tool.definitions.ts is hand-maintained and drifts from TOOL_DEFINITIONS — nothing enforces parity (the contract write tools were absent from financial for months). A parity test would prevent this class of drift.
  • The intent router's entity regexes (tool.handler.ts routeIntent) matched only singular nouns (\bcontract\b missed "contracts") until #238 added s?; check the other entity branches if router misses are reported.
  • exactOptionalPropertyTypes is on: optional result-object fields need explicit | undefined in their type when assigned from possibly-undefined sources.

Learnings - 2026-09-07

  • Auditing childCreate() call sites: every Autotask entity doc page carries a Parent Entity field, and the Tasks page states the rule — "If this entity has a Parent relationship, you must perform all Create, Update, and Delete actions on the parent entity." That field is the discriminator for whether POST /{Parent}/{id}/{Child} exists. TimeEntries says Parent: None, so its child routes never existed and every ticket-scoped time entry 404'd (#277). Audited all other childCreate callers at that time — all have documented parents.
  • Never add a 404 → POST /{Child} fallback inside childCreate(). On a write, a 404 is ambiguous between "route doesn't exist" and "parent id doesn't exist", so a silent retry turns "project 12345 doesn't exist" into a successfully created, mis-scoped record. childQuery's 404 → GET fallback is safe only because it's an idempotent read; do not extend that precedent to writes.
  • Removing a parameter from a tool's inputSchema does not stop callers sending it. There is no zod/ajv layer, additionalProperties is always true, and tool.handler.ts passes the whole args object into the service. Deprecating a parameter needs an explicit guard at the top of the handler closure (before any network call). Two now exist (projectID on create, projectId on search time entries) — if a third becomes necessary, that's the signal to add additionalProperties: false plus real validation instead of another if.
  • A bad query clause fails differently depending on which half is wrong, and the difference decides how dangerous it is:
    • Bad operator → silently dropped. { op: 'ne', … } (no such operator; it's noteq) was discarded and the call returned everything, reading as a filtered result. That's #193 — wrong data, no error.
    • Bad field name → hard error. { op: 'eq', field: 'projectID' } against TimeEntries returns HTTP 500: Unable to find projectID in the TimeEntry Entity. That's #277 — loud, and comparatively safe.

Read the full file on GitHub · 26 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 Changed · +11 lines · +568 tokens per session a50cf45879cc
  2. 10d ago First seen · 15 lines · 274 tokens per session scan A 1d5528376ed6

Subscribe to this mod's changes

autotask-mcp CLAUDE.md is an instructions file published in the GitHub repository WYRE-AI/autotask-mcp (50 stars, last pushed today), licensed Apache-2.0. It adds 842 tokens to every session, about $0.0042 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

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

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