ai-agents-research-methodology

ai-agents-research-methodology is a skill for Claude Code from rjmurillo/ai-agents. It costs 118 tokens per session (4,130 once invoked), scanned B, original, MIT.

A research process for turning an idea into a checked result through hypotheses, experiments, review decisions, and monitoring.

In plain words
What is it for?
Use it to design an investigation, record competing explanations, run a baseline evaluation, and decide whether a finding is ready to adopt.
Why use it?
It prevents plausible-sounding ideas from being accepted without evidence, including evidence from observations that contradict them.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions AGENTS.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/eval/eval-prompt-change.py \.

Part of the project-toolkit plugin — 113 skills, 26 commands, 33 agents, 4 hooks shipped together

Good fit Use it to design an investigation, record competing explanations, run a baseline evaluation, and decide whether a finding is ready to adopt.

Compare 6 skills from other repositories ↓
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/rjmurillo/ai-agents
agentmods
npx agentmods add skills/rjmurillo/ai-agents/ai-agents-research-methodology

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 113 skills, 26 commands, 33 agents, 4 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 ai-agents-research-methodology

README.md
[![agentmods](https://agentmods.dev/badge/skills/rjmurillo/ai-agents/ai-agents-research-methodology/github.svg)](https://agentmods.dev/skills/rjmurillo/ai-agents/ai-agents-research-methodology)
Your own site
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/ai-agents-research-methodology"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/ai-agents-research-methodology/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 ai-agents-research-methodology

Your own site · 80×15
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/ai-agents-research-methodology"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/ai-agents-research-methodology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,130 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 269
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • high Agent Snooping · line 272
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • medium Agent Snooping · line 269
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 270
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00118 $0.04130
Opus 5 $0.00059 $0.02065
Sonnet 5 $0.00024 $0.00826
Haiku 4.5 $0.00012 $0.00413

Measured 7d ago against content hash 7141af7456e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

ai-agents-research-methodology scanned grade B with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (tests/test_structure_ai_agents_research_methodology.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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| Contradiction log format | `.claude/rules/search-before-building.md` | `grep -n "decision-" .claude/rules/search-before-building.md` |
.claude/skills/ai-agents-research-methodology/SKILL.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agents Research Methodology

This repo runs on verification-based governance: labels like "MANDATORY" or "NON-NEGOTIABLE" are insufficient, every requirement needs a verification mechanism. The same standard applies to ideas. An idea is not accepted because it sounds right, because a model agreed with it, or because a retro asserted it. It is accepted when it survives the lifecycle below and leaves an inspectable artifact at every stage.

This skill is the discipline. For the specific probe recipes, use ai-agents-empirical-probe-toolkit. For the three open research programs, use ai-agents-research-frontier. For the archive of past settled results, use ai-agents-failure-archaeology.

Triggers

  • how do I prove this idea
  • run the idea lifecycle
  • what is the evidence bar
  • turn this hunch into a result

The Evidence Bar

A result is accepted here when ONE mechanism explains ALL observations, including the negative ones, and the explanation survives adversarial refutation. Partial explanations that cover only the confirming observations are hypotheses, not results.

The cautionary tale is PR #1989. Mitigation M1 was built on a root-cause claim inherited from a retro RCA that nobody re-verified: the RCA said pagination was missing, but get_unresolved_review_threads.py already paginated correctly (.agents/retrospective/2026-05-10-pr-1989-recursive-failure.md:20). Five commits were spent building on the false premise. The mechanism-check that would have caught it costs one file read.

Map each claim type to the adversarial machinery that already exists. Do not invent a new review ritual; route into these:

Claim type Adversarial mechanism How to invoke
Architectural decision (ADR) adr-review 6-agent debate (architect, critic, independent-thinker, security, analyst, high-level-advisor) until consensus, 10 rounds max Auto-fires on any ADR-*.md create/edit (AGENTS.md "ADR Review"); or /adr-review path
A single decision's reasoning decision-critic skill Say Poke holes in this decision or Validate my thinking on ...
Contrarian read of a plan independent-thinker or critic agent (.claude/agents/) Task tool with that subagent_type
Strategic build/buy/defer buy-vs-build-framework (Quick tier: 1-2 hours) Required gate for new capabilities, see Phase 3
"Why does this constraint exist" chestertons-fence Before proposing removal of anything settled
Behavioral claim about a prompt or rule Eval harness (ADR-057) See Predict Numbers Before Running
Prose claims in the write-up prose-self-check, doc-accuracy Before emitting the artifact

Read the full file on GitHub · 282 lines

Files

What ships with it

1 file 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. 7d ago First seen · 282 lines · 118 tokens per session scan B 7141af7456e2

Subscribe to this mod's changes

ai-agents-research-methodology is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 4,130 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.