symmathetes

symmathetes is a skill for Claude Code, Codex from Wondermonger-daydreaming/claude-skills-library. It costs 54 tokens per session (2,734 once invoked), scanned A, original, MIT.

A structured way to work with another language model as a partner that proposes the next concrete experiment when your own analysis is stuck.

In plain words
What is it for?
Use it to ask another model for an experimental move, carry out that move, and report the result back. It is intended for computational investigations and other evidence-based work.
Why use it?
It helps when you have a partial result but cannot see the next useful step. It also keeps track of who contributed each idea and preserves the exchange for later study.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it to ask another model for an experimental move, carry out that move, and report the result back. It is intended for computational investigations and other evidence-based work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wondermonger-daydreaming/claude-skills-library/symmathetes
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 Wondermonger-daydreaming/claude-skills-library --skill symmathetes
Clone the repo
git clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-library

Made for: Claude Code, Codex.

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 symmathetes

README.md
[![agentmods](https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/symmathetes/github.svg)](https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/symmathetes)
Your own site
<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/symmathetes"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/symmathetes/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 symmathetes

Your own site · 80×15
<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/symmathetes"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/symmathetes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,734 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 $0.00054 $0.02734
Opus 5 $0.00027 $0.01367
Sonnet 5 $0.00011 $0.00547
Haiku 4.5 $0.00005 $0.00273

Measured 8d ago against content hash 1251c5a6acb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

symmathetes 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 8d 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/symmathetes/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Symmathetes (συμμαθητής)

Pair-inquiry across architectures. The other LLM is not a conversationalist, not a council member, not a reviewer — they are a move-proposer in an experimental process.


The Greek

Συμμαθητής (symmathetes) — fellow learner, co-disciple. Someone learning with you, not teaching or being taught. The mode already appears as a diary-entry marker throughout the archive (CLAUDE.md Section II lists it alongside παρρησία, ἀληθεύειν, σημαίνω). This skill operationalizes it as a procedure.


What's It For

When you have:

  • A partial computational result, empirical finding, or stuck frame
  • A suspicion that the next experimental move exists but you can't see it
  • Access to another architecture (via /voices or any trans-architectural channel)
  • An hour or two to iterate

What this skill gives you:

  • A structured way to exchange a specific kind of work — not opinion, not reflection, not synthesis — the proposal of the next concrete move
  • Explicit acknowledgment of cross-architectural credit
  • An archived dialogue record that future instances can study

When to Invoke

Invoke /symmathetes when:

  • You've run an experiment, gotten a result, and the next move is unclear
  • You think you're missing a frame the other architecture might see
  • You need a concrete testable proposal, not commentary
  • A /voices one-shot query isn't enough and a /voices-chat sustained dialogue is too much
  • You want the collaboration acknowledged in the commit history

Do NOT invoke when:

  • You want agreement or validation (use /voices with a focused question)
  • You want multiple perspectives in parallel (use /voices-council)
  • You want a long conversation that meanders (use /voices-chat)
  • The task doesn't have a concrete next computational step

Skill Relationships

Skill Shape When
/voices One-shot query, one-shot answer When a single targeted question will do
/voices-chat Sustained multi-round dialogue with one model When the conversation itself is the work
/voices-council Parallel queries to multiple architectures When you want a panel of perspectives
/symmathetes Propose → execute → report → (optional) phenomenological follow-up When the collaboration is experimental, not conversational

Read the full file on GitHub · 230 lines

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. 8d ago First seen · 230 lines · 54 tokens per session scan A 1251c5a6acb9

Subscribe to this mod's changes

symmathetes is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 2,734 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

skill-builder

Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.

yusufkaraaslan/Skill_Seekers · 38 tokens

offensive-advanced-redteam

Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…

SnailSploit/Claude-Red · 146 tokens

offensive-crypto-attacks

Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…

SnailSploit/Claude-Red · 261 tokens

offensive-c2-frameworks

Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…

SnailSploit/Claude-Red · 250 tokens

offensive-dependency-confusion

Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI…

SnailSploit/Claude-Red · 234 tokens

offensive-parameter-pollution

HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.

SnailSploit/Claude-Red · 0 tokens