elenchus

elenchus is a skill for Claude Code, Codex from Shogo1222/socratic. It costs 119 tokens per session (5,366 once invoked), scanned A, original, MIT.

A method for assessing whether a test suite protects the software behavior that matters most by challenging tests with plausible code changes.

In plain words
What is it for?
Use it to review existing or changed tests, rank risks, analyze which intentional changes tests catch, and specify missing tests in isolated workspaces.
Why use it?
It helps find important behaviors that tests do not cover and distinguish meaningful protection gaps from less important coverage results.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions subagents.

Part of the socratic plugin — 3 skills, 3 hooks shipped together

Good fit Use it to review existing or changed tests, rank risks, analyze which intentional changes tests catch, and specify missing tests in isolated workspaces.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shogo1222/socratic/elenchus
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 Shogo1222/socratic --skill elenchus
Clone the repo
git clone --depth 1 https://github.com/Shogo1222/socratic

Made for: Claude Code, Codex.

Or install socratic, the plugin that ships this one along with the rest of its 3 skills, 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 elenchus

README.md
[![agentmods](https://agentmods.dev/badge/skills/shogo1222/socratic/elenchus/github.svg)](https://agentmods.dev/skills/shogo1222/socratic/elenchus)
Your own site
<a href="https://agentmods.dev/skills/shogo1222/socratic/elenchus"><img src="https://agentmods.dev/badge/skills/shogo1222/socratic/elenchus/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 elenchus

Your own site · 80×15
<a href="https://agentmods.dev/skills/shogo1222/socratic/elenchus"><img src="https://agentmods.dev/badge/skills/shogo1222/socratic/elenchus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,366 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 $0.00119 $0.05366
Opus 5 $0.00060 $0.02683
Sonnet 5 $0.00024 $0.01073
Haiku 4.5 $0.00012 $0.00537

Measured 9d ago against content hash 7e35a8f337ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

elenchus 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/isolation_gate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/elenchus/SKILL.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Elenchus

Challenge a test suite with plausible misunderstandings of programming intent. Optimize for confidence in important behavior, not mutation score. Mutation is the internal evidence engine, not the headline: report each result as the incident it represents, never as an operator name or a score.

Required references

Read references/mutation-design.md before generating mutants and references/safety.md before changing or executing code. When a proposed test is proved or applied, read references/test-handoff.md. In standalone use only, validate inputs and outputs with the bundled intent-contract.schema.json, mutation-result.schema.json, mutation-report.schema.json, and test-handoff.schema.json. Under a Socratic-hosted run, never open schema files: every document starts from a Runner scaffold whose editable_fields and field_guide carry the authoritative structure, and the Runner performs all validation.

Git safety boundary

Use local Git only for strictly read-only evidence gathering. Allowed commands are limited to git diff, git show, git log, git rev-parse, git merge-base, and git ls-files; git archive is not read-only (-o writes a file) and the Host gate denies it. During an active hook-host run, prefix each with git --no-pager; add --no-ext-diff --no-textconv to diff, show, and log. Never change local or remote Git state. Never run any staging, commit, amend, push, pull, fetch, checkout, switch, reset, stash, merge, rebase, cherry-pick, branch, tag, or worktree operation. Never invoke gh or a code-host write API. Do not request permission to perform a prohibited operation.

Materialize Base and Head as disposable filesystem snapshots without branch switching or Git worktrees. If the required object is unavailable locally and obtaining it would require fetch, stop and report the snapshot as unavailable.

Read the full file on GitHub · 279 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. 9d ago First seen · 279 lines · 119 tokens per session scan A 7e35a8f337ba

Subscribe to this mod's changes

elenchus is a skill published in the GitHub repository Shogo1222/socratic (5 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 5,366 once invoked, about $0.0006 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.