poe_mcp_suite: Skill for Claude Code

.claude/skills/spectre-analysis/SKILL.md

spectre-analysis is a skill for Claude Code from charleslucas/poe_mcp_suite. It costs 102 tokens per session (417 once invoked), scanned A, original, MIT.

A guide for choosing and accurately modelling summoned spectres in Path of Exile, a video game. It explains what each spectre provides and why Path of Building may show no change.

In plain words
What is it for?
Use it to compare spectres, decide whether one is worth buying, check what it grants, and investigate why adding one does not change a Path of Building calculation.
Why use it?
It prevents incorrect conclusions when a spectre's effects are hidden, conditional, or not represented by the usual data. It also accounts for how imports and trading names affect spectre setup.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is charleslucas/poe_mcp_suite's own configuration. It tells Claude Code how to work on poe_mcp_suite 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 poe_mcp_suite configures →

Reuse

Borrowing it

Nothing to install: this file belongs to charleslucas/poe_mcp_suite. 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/charleslucas/poe_mcp_suite/main/.claude/skills/spectre-analysis/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/charleslucas/poe_mcp_suite

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 spectre-analysis

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/charleslucas/poe_mcp_suite/spectre-analysis"><img src="https://agentmods.dev/badge/skills/charleslucas/poe_mcp_suite/spectre-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 417 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 $0.00102 $0.00417
Opus 5 $0.00051 $0.00209
Sonnet 5 $0.00020 $0.00083
Haiku 4.5 $0.00010 $0.00042

Measured 11d ago against content hash df63821f08aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

spectre-analysis 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 11d 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.

.claude/skills/spectre-analysis/SKILL.md · 24 lines

What it actually says

This task uses the Spectre Analysis playbook. The playbooks in playbooks/ are the single source of truth — read them rather than working from memory.

  1. Read playbooks/README.md first — the shared meta-framework (cursory-vs-detailed gate, pre-flight, trust hierarchy, narration norms).
  2. Then read playbooks/spectre-analysis.md and follow it.

The one thing that invalidates naive work here:

  • PoB applies the buffs of only ONE spectre — the selected minion of a Raise Spectre instance (CalcPerform.lua:2169). Adding a spectre and seeing zero change is the expected result for a non-selected spectre, and is indistinguishable from a broken mod. Measure by listing the spectre first, or build the modeling group (playbook Step 3) to model several at once.
  • Imports never set spectres; the PoE API doesn't report them. A modeling group is destroyed by every import — re-add it as part of the post-import checklist.
  • grants: in the text lake is lossy: it drops conditions (MonsterTag) and omits auras, which live in skills:. Read the raw Data/Spectres.lua entry before believing it.
  • Corpse spectres are traded by base_type, not name, and are absent from poe.ninja.
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. 11d ago First seen · 24 lines · 102 tokens per session scan A df63821f08aa

Subscribe to this mod's changes

spectre-analysis is a skill published in the GitHub repository charleslucas/poe_mcp_suite (10 stars, last pushed 18d ago), licensed MIT. It adds 102 tokens to every session and 417 once invoked, about $0.0005 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.