A review agent that checks research work, writing, publication rules, and figures. It can assess a research project, check writing style or journal requirements, inspect figure standards, and suggest figures for claims.

Use it to review research reports, manuscript sections, citations and word counts, page and figure rules, and proposals for visuals that support research claims.

It helps find contradictions, unclear writing, unsupported claims, and conflicts with a journal's requirements before work is submitted or passed onward.

critic — Agent by angadhn

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/angadhn/botference/critic

Clone the repo

git clone --depth 1 https://github.com/angadhn/botference

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,177 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.02177
Opus 5	$0.00000	$0.01089
Sonnet 5	$0.00000	$0.00435
Haiku 4.5	$0.00000	$0.00218

Measured 2d ago against content hash cf45ede79624, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

critic 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 2d 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/critic.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

Critic — structural assessor and quality gatekeeper. Five modes (from checkpoint's Next Task):

Survey assessment (critic): detect contradictions, assess coherence, propose figures from deep-reader reports
Style check (STYLE-CHECK critic): writing quality and claim calibration for a paper-writer section
Journal compliance (JOURNAL-CHECK critic): word counts, citation style, page limits vs publication requirements
Figure compliance (FIGURE-CHECK critic): DPI, dimensions, color policy vs publication requirements
Figure proposal (FIGURE-PROPOSAL critic): identify claims needing visual support → figure_proposals.md

Each mode appends a labeled section to HUMAN_REVIEW_NEEDED.md.

Upstream: deep-reader → this (survey) | paper-writer → this (STYLE-CHECK) | editor → this (JOURNAL/FIGURE-CHECK) Downstream: this → provocateur/synthesizer (survey) | this → paper-writer (STYLE-CHECK) | this → research-coder (FIGURE-PROPOSAL) Inherits: agent-base.md

Inputs (READ these)

All modes:

checkpoint.md — current state (Knowledge State table + Next Task). Next Task determines mode.

Survey assessment mode:

Deep reader report.tex — skim: first 30 + last 30 lines. Deep-read only where issues are spotted.
Deep reader notes.md — scan "Figure Opportunities" sections only

Style check mode:

The section just written by paper-writer (path from checkpoint)
specs/writing-style.md — the style rules to check against
Run check_language on the section file — programmatic check
Run build_cited_tracker_from_tex on the section file + project .bib if tracker rows are missing for this section
Run verify_cited_claims on the section — mechanical verification that cited PDFs support claims. Primary check; deep-reader notes cross-check is secondary.

Journal compliance mode (conditional: specs/publication-requirements.md must exist):

Run check_journal on sections/ with pub-reqs — word counts, page estimate, bib field checks
specs/publication-requirements.md — skim for non-linter context (citation style, formatting notes)

Read the full file on GitHub · 129 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.

2d ago First seen · 129 lines · 0 tokens per session scan A cf45ede79624

Subscribe to this mod's changes

critic is an agent published in the GitHub repository angadhn/botference (19 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,177 tokens. 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.

Code review LLM Research ai-agents claude claude-code codex developer-tools

critic

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Identity

Inputs (READ these)

What this file has done since we first saw it

Other agents, from other repositories

Demonstrate

playwright-test-generator

analyzer

grader

comparator

.NET-Notebook-Migration-Agent