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/calebgerman/mcp-taskflow/copilot-instructionsgit clone --depth 1 https://github.com/CalebGerman/mcp-taskflowWhat 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 | $0.00793 | $0.00793 |
| Opus 5 | $0.00396 | $0.00396 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
mcp-taskflow 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 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TaskFlow MCP - AI Coding Agent Guide
Project Overview
TaskFlow MCP is a Model Context Protocol (MCP) server built with Node.js and TypeScript. It provides structured planning, execution tracking, and research workflows for AI agents via MCP tools.
MCP Tool Preferences
- Primary code navigation & edits: Serena MCP tools.
- Planning & task workflows: TaskFlow MCP tools.
- Research: Playwright MCP tools (preferred).
Required workflow
- Always use TaskFlow MCP tools for planning and task workflows.
- If tests exist for the change, run them and include results in verification criteria.
- Commit after finishing every task.
Security-First Operating Mode
Security is non-negotiable. Prioritize secure-by-design solutions over functionality, performance, or speed. Before making changes, perform a brief security analysis:
- Threat model: trust boundaries, data flows, threat actors (STRIDE).
- Security requirements: authn/authz, input validation, encryption needs.
- Attack vectors: injection, broken auth, access control, SSRF, deserialization, secrets exposure.
OWASP-Aligned Expectations (Condensed)
- Validate all inputs (allowlist, server-side).
- Enforce access control for every operation; prevent IDOR.
- Protect data (TLS 1.2+, no secrets in code or logs).
- Handle errors securely (generic user errors, detailed logs only).
- Use vetted security libraries; never roll your own crypto.
Verification Checklist (Required)
- Security tests for negative cases (validation, authz).
- No hardcoded secrets or sensitive data in logs.
- Build/tests pass; no security warnings.
Avoid using ref-based research tools in this repo.
Architecture & Structure
Layered Design
Config (src/config/) → Data (src/data/) → Tools (src/tools/) → Server (src/server/) → MCP Client
↓
Prompts (src/prompts/)
- Config: Workspace and data path resolution (see
src/config/pathResolver.ts) - Data: JSON persistence and domain models (see
src/data/) - Tools: MCP tool implementations by domain (see
src/tools/) - Server: MCP server setup and lifecycle (see
src/server/) - Prompts: Markdown templates for tool responses (see
src/prompts/)
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.
- yesterday First seen · 103 lines · 793 tokens per session scan A dd82b61eaee2
mcp-taskflow copilot-instructions.md is an instructions file published in the GitHub repository CalebGerman/mcp-taskflow (0 stars, last pushed 6mo ago), licensed MIT. It adds 793 tokens to every session, about $0.0040 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
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.
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).
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.