patpat-impact

patpat-impact is a skill for Cursor from goiltpatpat/patpat. It costs 45 tokens per session (389 once invoked), scanned A, original, MIT.

A read-only repository-analysis tool that traces which parts of a codebase a change could affect.

In plain words
What is it for?
Reviewing risky code changes, tracing callers and data flow, checking stored or transmitted formats, and assessing generated or operational outputs.
Why use it?
It helps identify downstream breakage and test whether a supposedly small change crosses important boundaries.

Skill for Cursor

Written for Cursor: shipped in a Cursor plugin.

Part of the patpat plugin — 22 skills, 1 agent, 3 hooks shipped together

Good fit Reviewing risky code changes, tracing callers and data flow, checking stored or transmitted formats, and assessing generated or operational outputs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goiltpatpat/patpat/patpat-impact
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.

Any agent
npx skills add goiltpatpat/patpat --skill patpat-impact
Clone the repo
git clone --depth 1 https://github.com/goiltpatpat/patpat

Made for: Cursor.

Or install patpat, the plugin that ships this one along with the rest of its 22 skills, 1 agent, 3 hooks.

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 patpat-impact

README.md
[![agentmods](https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-impact/github.svg)](https://agentmods.dev/skills/goiltpatpat/patpat/patpat-impact)
Your own site
<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-impact"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-impact/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 patpat-impact

Your own site · 80×15
<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-impact"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-impact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 389 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00045 $0.00389
Opus 5 $0.00023 $0.00195
Sonnet 5 $0.00009 $0.00078
Haiku 4.5 $0.00005 $0.00039

Measured 7d ago against content hash 27f70cc13ac8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

patpat-impact 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 7d 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.

skills/patpat-impact/SKILL.md · 19 lines

What it actually says

Patpat Impact

When invoked directly, read the operating protocol in full. Do not load the router.

Read repository truth, boundary discipline, and proof over proxy. Apply the blast-radius playbook.

The job is the one-safety-fact the change depends on, not a caller list. Grep callers is not the deliverable. Climb the certainty ladder for that fact and say where it stopped: (1) said so (worthless alone) (2) pointed at file:line (3) walked the failure and it does not reach (4) ran real code (a script or test that calls the shipped function and fails loud if wrong) (5) reproduced in the running app. Any fact that does not reach ladder step 4 is unproven. Do not write it as settled.

Remain read-only. Hand back, small: what it does; the one fact, the step reached, and the proof or unproven; real risks with file:line; cleared; cheapest check before merge. Do not turn blast-radius analysis into architecture design or implementation.

Mutation boundary

Remain read-only with respect to repository implementation and external delivery. Limit incidental verifier artifacts to the declared proof contract, clean them up, and hand any authorized mutation back to patpat-loop.

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. 7d ago Changed 27f70cc13ac8
  2. 10d ago First seen · 19 lines · 45 tokens per session scan A dc364e607bb9

Subscribe to this mod's changes

patpat-impact is a skill published in the GitHub repository goiltpatpat/patpat (1 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 389 once invoked, about $0.0002 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.