pn-tool-risk-policy

pn-tool-risk-policy is a cursor rule for Cursor from perniemann/pnCore. It costs 356 tokens per session, scanned A, original, MIT.

A policy for deciding how risky tool calls are and when a human must approve them. It separates read-only actions, append-only logs, approval gates, and external production changes.

In plain words
What is it for?
Use it when reviewing tool workflows, adding approval checkpoints, recording gate outcomes, or auditing human-in-the-loop processes.
Why use it?
It makes workflow audits safer by ensuring sensitive or externally visible actions are logged and approved at the appropriate point.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it when reviewing tool workflows, adding approval checkpoints, recording gate outcomes, or auditing human-in-the-loop processes.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/perniemann/pncore/pn-tool-risk-policy
Install

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.

Clone the repo
git clone --depth 1 https://github.com/perniemann/pnCore

Made for: Cursor.

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 pn-tool-risk-policy

README.md
[![agentmods](https://agentmods.dev/badge/rules/perniemann/pncore/pn-tool-risk-policy/github.svg)](https://agentmods.dev/rules/perniemann/pncore/pn-tool-risk-policy)
Your own site
<a href="https://agentmods.dev/rules/perniemann/pncore/pn-tool-risk-policy"><img src="https://agentmods.dev/badge/rules/perniemann/pncore/pn-tool-risk-policy/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 pn-tool-risk-policy

Your own site · 80×15
<a href="https://agentmods.dev/rules/perniemann/pncore/pn-tool-risk-policy"><img src="https://agentmods.dev/badge/rules/perniemann/pncore/pn-tool-risk-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 356 This file is loaded in full into every session.
When invoked 356 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 $0.00356 $0.00356
Opus 5 $0.00178 $0.00178
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00036 $0.00036

Measured 5d ago against content hash 6fece9737274, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pn-tool-risk-policy 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.

packages/pn-core-mcp/content/rules/pn-tool-risk-policy.mdc · 23 lines

What it actually says

Tool risk policy (pn-core MCP)

Tier Tools Expectation
Read-only list_*, get_*, health, list_workflow_types, workflow_step, workflow_confirm, workflow_usage_totals, workflow_handoff_read, workflow_state_load No workspace writes; safe to call freely.
Append-only JSONL report_usage, gate_log_append, workflow_handoff_append, workflow_state_save Writes under cwd only via path rules; prefer .pncore/ paths. Idempotent or append-only semantics.
Gate / secret approval_checkpoint Requires PNCORE_APPROVAL_TOKEN on server; optional workflow_type + workflow_step + run_id for human-gate tickets.
External side effects paperclip_issue_* Requires Paperclip env; treat as production API calls.

Workflow human gates

  • Optional mandatory human gates: PNCORE_REQUIRE_APPROVAL_FOR_WORKFLOWS — each human workflow_step needs a fresh approval_checkpoint ticket.
  • Echo run_id from workflow_step in state for every call; pass the same run_id to approval_checkpoint when issuing tickets so tickets bind to the run.

Audit

  • After gate outcomes, call gate_log_append with optional run_id for correlation with .pncore/workflow-runs.jsonl.
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. 5d ago First seen · 23 lines · 356 tokens per session scan A 6fece9737274

Subscribe to this mod's changes

pn-tool-risk-policy is a cursor rule published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 356 tokens to every session, about $0.0018 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 2026-09-03.