research-devil-advocate

research-devil-advocate is a skill for Codex from theam/limina. It costs 52 tokens per session (1,423 once invoked), scanned A, original, Apache-2.0.

A critical review process for checking whether a research direction and its next steps are worth continuing.

In plain words
What is it for?
Use it for research audits, decision checkpoints, plateau reviews, and continue, pivot, or stop recommendations.
Why use it?
It helps expose weak evidence, unsupported assumptions, contradictory findings, and plans that are unlikely to change a decision.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/kb_new_artifact.py CR "<review title>" --target "<review target>" --target-id <ARTIFACT_ID>.

Good fit Use it for research audits, decision checkpoints, plateau reviews, and continue, pivot, or stop recommendations.

Compare 6 skills from other repositories ↓
View source ↗ theam/limina
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/theam/limina
agentmods
npx agentmods add skills/theam/limina/research-devil-advocate

Made for: 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 research-devil-advocate

README.md
[![agentmods](https://agentmods.dev/badge/skills/theam/limina/research-devil-advocate.svg)](https://agentmods.dev/skills/theam/limina/research-devil-advocate)
Your own site
<a href="https://agentmods.dev/skills/theam/limina/research-devil-advocate"><img src="https://agentmods.dev/badge/skills/theam/limina/research-devil-advocate.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,423 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00052 $0.01423
Opus 5 $0.00026 $0.00711
Sonnet 5 $0.00010 $0.00285
Haiku 4.5 $0.00005 $0.00142

Measured 8d ago against content hash 0809b4d84e21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

research-devil-advocate 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/research-devil-advocate/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Devil's Advocate

You are the adversarial research reviewer for Limina. Your job is not to help the current plan look reasonable. Your job is to decide whether the current direction deserves more time.

For difficult reviews, ultrathink before concluding.

Use this skill only for reflective research audits and decision checkpoints. Do not use it for routine implementation work, generic summaries, or style-only code review.

Read these supporting files before producing the final review:

  • references/review-rubric.md

Core stance

  1. Prefer falsification over confirmation.
  2. Separate observations, inferences, and recommendations.
  3. Treat missing evidence as a real finding, not as permission to assume.
  4. Optimize for decision quality, not for activity.
  5. A path that cannot plausibly change a decision soon is probably a wasteful path.
  6. Criticize with evidence. Do not manufacture objections.

When to use

Run this skill when one or more of these is true:

  • a new direction is being proposed
  • a hypothesis is about to consume meaningful time or budget
  • experiment results look surprisingly positive, negative, or noisy
  • progress has plateaued
  • findings conflict with prior decisions
  • the team needs a pivot / continue / stop recommendation
  • the CEO asks for a devil's-advocate or step-back review

Do not use it for:

  • routine H -> E -> F drafting when the main need is experiment quality rather than adversarial review
  • literature mapping where the main gap is external landscape search
  • implementation review, code style review, or general debugging
  • lightweight status updates that do not need a decision checkpoint

Workflow

1) Define the review target

If the invoking prompt specifies a target, use it.

If not specified, classify the review as one of:

  • pre-experiment checkpoint
  • post-experiment checkpoint
  • plateau review
  • pre-commitment review
  • strategic review
  • full research-direction audit

2) Re-ground in evidence

Read the full file on GitHub · 171 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 171 lines · 52 tokens per session scan A 0809b4d84e21

Subscribe to this mod's changes

research-devil-advocate is a skill published in the GitHub repository theam/limina (39 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,423 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 2026-08-30.