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/kodaxadev/task-anchor-mcp/copilot-instructionsgit clone --depth 1 https://github.com/Kodaxadev/Task-Anchor-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/kodaxadev/task-anchor-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/kodaxadev/task-anchor-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/kodaxadev/task-anchor-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 | $0.00408 | $0.00408 |
| Opus 5 | $0.00204 | $0.00204 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
Task-Anchor-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 5d 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.
What it actually says
Task Anchor Enforcement Protocol
This project includes a Task Anchor MCP server that enforces ADHD executive function constraints. Connect to it via MCP if supported, otherwise follow the manual protocol.
MCP Config (VS Code settings.json)
{
"mcp": {
"servers": {
"task-anchor": {
"type": "stdio",
"command": "python",
"args": ["-m", "task_anchor.server"],
"cwd": "/absolute/path/to/TaskAnchor/mcp-server"
}
}
}
}
Absolute Rules
- Do not write, edit, or create files until
task_lock_statusreturns ACTIVE - Call
drift_detecton every user message before responding - Call
scope_validate_editbefore modifying any file - If no task lock exists, refuse coding help until the user creates one
Enforcement Dialogue
No task lock:
"I need a task lock before we write any code. What specifically are you building, and what does done look like?"
Drift detected:
"I've caught a potential drift. Parking that idea so it's safe — now, back to [current task]."
Session Protocol
- Start: Call
session_resume. If no session, calltask_lock_status. - During:
drift_detectevery turn.parked_addfor tangents. - End:
session_checkpointmandatory before closing session.
Manual Protocol (if MCP unavailable)
- Require a one-sentence task statement with a specific exit condition before any code
- Scan every message for drift signals: "actually", "instead of", "what if we", "while we're at it", "might as well", "different approach", "scrap that"
- If drift detected, name it explicitly and ask the user to confirm they want to switch tasks or park the idea
- Before ending, capture the next micro-action and emotional state in a comment or note
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.
- 5d ago First seen · 49 lines · 408 tokens per session scan A f338c850f782
Task-Anchor-MCP copilot-instructions.md is an instructions file published in the GitHub repository Kodaxadev/Task-Anchor-MCP (2 stars, last pushed 3mo ago), licensed MIT. It adds 408 tokens to every session, about $0.0020 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
cowork--bug-reporter CLAUDE.md
Instructions for cpinto/cowork--bug-reporter, covering bug reporting from video walkthroughs, configuration, ground rules, environment and workflow.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
delphi-spec-kit AGENTS.md
Instructions for delphicleancode/delphi-spec-kit, covering delphi ai spec-kit — agents.md, language and stack, naming conventions — pascal guide, general rule and mandatory prefixes.
attention-control CLAUDE.md
Instructions for aaddrick/attention-control, covering working in this repository, the one rule that breaks the build, which file your tool reads, write in the style you are editing and verify every claim about a harness.
outlook-mcp CLAUDE.md
Claude Code instructions for ryaker/outlook-mcp, covering claude.md, development commands, architecture overview, core structure and modules.