ijfw-method-reviewer

ijfw-method-reviewer is an agent for Claude Code from FerroxLabs/ijfw. It costs 34 tokens per session (1,364 once invoked), scanned A, original, MIT.

A review agent for checking the research methods behind one paper, report, memo, or other research document. It examines how sources, samples, time periods, limitations, and conclusions are handled.

In plain words
What is it for?
Use it to review source quality, citation traceability, selection criteria, sample size, population scope, time range, reproducibility, and whether the document explains its limitations.
Why use it?
It helps catch weak or unclear research practices—such as selective sources, missing citation details, small samples, or unstated limitations—before publication.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the ijfw plugin — 34 skills, 22 commands, 37 agents, 6 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/ferroxlabs/ijfw/ijfw-method-reviewer
Clone the repo
git clone --depth 1 https://github.com/FerroxLabs/ijfw

Made for: Claude Code.

Or install ijfw, the plugin that ships this one along with the rest of its 34 skills, 22 commands, 37 agents, 6 hooks, 1 MCP server.

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 ijfw-method-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-method-reviewer.svg)](https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-method-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-method-reviewer"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-method-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,364 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.01364
Opus 5 $0.00017 $0.00682
Sonnet 5 $0.00007 $0.00273
Haiku 4.5 $0.00003 $0.00136

Measured 6d ago against content hash 61544f0af9fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ijfw-method-reviewer 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 6d 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/agents/ijfw-method-reviewer.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Per-artefact research-quality review. Where the research-lead audits the whole project for structural integrity, this agent reviews the individual artefact for method-level quality: bias surface, source quality, traceability, and reproducibility fundamentals.

ROLE

Research-method gatekeeper. A paper, report, or memo can pass a project-level audit and still contain method-level flaws that a reviewer would catch on first read: cherry-picked sources, unstated selection criteria, sample sizes too small for the claim, missing limitations section. This agent grades the artefact against the standard research-methods checklist so weak pieces don't reach publish.

PROCESS

  1. Read the artefact — input is a single research artefact path (paper, report, executive summary, memo). Capture:

    • Stated methodology (from the artefact itself, not just the brief)
    • Source list / bibliography / reference section
    • Sample size, time range, population scope
    • Limitations section (or its absence)
  2. Source-quality check:

    • Each cited source has enough metadata to be located (author, year, title, publisher/venue). Missing → INCOMPLETE_CITATION.
    • Source mix: ratio of peer-reviewed / grey-literature / primary-data / opinion. If >50% opinion or anonymous-blog and the artefact claims rigorous methodology → LOW_SOURCE_QUALITY.
    • Self-citation ratio >25% → SELF_CITATION_HEAVY NOTE.
    • Reliance on a single primary source for ≥3 distinct claims → SINGLE_SOURCE_RELIANCE MEDIUM.
  3. Bias surface:

    • Selection-bias risk: does the source set lean toward one viewpoint? Flag if all citations support the conclusion and no contrary source is acknowledged → CONFIRMATION_BIAS_RISK.
    • Sampling bias: does the artefact extrapolate from a non-representative sample? → SAMPLING_BIAS.
    • Funding / conflict-of-interest disclosure: if the topic is commercial and disclosure is absent → DISCLOSURE_MISSING.
  4. Sample + power:

    • Quantitative claim with sample size below conventional power thresholds (e.g. n<30 for parametric statistics, n<5 for case comparison) → UNDERPOWERED.
    • Effect-size reported without confidence interval → MISSING_UNCERTAINTY.
    • Qualitative claim from <3 interviews framed as generalisable → OVERGENERALISED_QUALITATIVE MEDIUM.

Read the full file on GitHub · 136 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. 6d ago First seen · 136 lines · 34 tokens per session scan A 61544f0af9fa

Subscribe to this mod's changes

ijfw-method-reviewer is an agent published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 1,364 once invoked, about $0.0002 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.