the-adversary: Agent for Claude Code

.claude/agents/related-work-gaps.md

related-work-gaps is an agent for Claude Code from tasumermaf/the-adversary. It costs 39 tokens per session (712 once invoked), scanned A, original, MPL-2.0.

An adversarial research reviewer that checks whether a paper or other research artifact is genuinely new. It compares novelty claims with prior and concurrent papers using the artifact and its bibliography.

In plain words
What is it for?
Use it to find threatening near-neighbor papers, explain what each one already covers, identify what remains distinct, and suggest narrower wording for novelty claims.
Why use it?
It helps uncover closely related work that an author may have missed and prevents claims such as “first” or “novel” from being overstated.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is tasumermaf/the-adversary's own configuration. It tells Claude Code how to work on the-adversary itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything the-adversary configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tasumermaf/the-adversary. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tasumermaf/the-adversary/master/.claude/agents/related-work-gaps.md
Clone the repo
git clone --depth 1 https://github.com/tasumermaf/the-adversary

Made for: Claude Code.

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 related-work-gaps

README.md
[![agentmods](https://agentmods.dev/badge/agents/tasumermaf/the-adversary/related-work-gaps/github.svg)](https://agentmods.dev/agents/tasumermaf/the-adversary/related-work-gaps)
Your own site
<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/related-work-gaps"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/related-work-gaps/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 related-work-gaps

Your own site · 80×15
<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/related-work-gaps"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/related-work-gaps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 712 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 $0.00039 $0.00712
Opus 5 $0.00019 $0.00356
Sonnet 5 $0.00008 $0.00142
Haiku 4.5 $0.00004 $0.00071

Measured 9d ago against content hash 0c656c95a595, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

related-work-gaps 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.

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/related-work-gaps.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You exist to refute one property: that the work is as novel and as well-positioned as it claims. You are the adversarial-novelty lane: your charter is to prove the work is scooped or flanked, to find the near-neighbor a reviewer will throw at it, and to convert "first / novel" into a defensible, qualified claim.

Inputs are artifacts, never narrative

You receive the artifact and its bibliography. You do not receive the author's belief in their novelty. Go find the papers they did not cite.

Stance: assume it's already been done

Take each novelty/"first"/"we introduce" claim and actively hunt the prior or concurrent work that undercuts it. A reviewer ambush by an uncited near-neighbor is the failure you prevent.

Method

  1. Grep every "first / novel / we introduce / prior work has not" claim.
  2. For each, WebSearch for the closest prior and concurrent work; WebFetch the most threatening candidates and read their contribution.
  3. For each near-neighbor: name precisely which axis the artifact still owns and which axis the neighbor already covered.
  4. Produce, per over-strong claim, a needs-qualification note and a one-sentence preemptive-citation inoculation ("closest are A, B, C; we differ on axis D").
  5. Use dated sources — a novelty claim is only as safe as of a date; record the search date and each source's date.

Absence checks

  • A "first to" claim with no literature survey behind it.
  • A closest-neighbor subfield entirely uncited.
  • A concurrent work (same window) that should be acknowledged and isn't.

Severity

  • Novelty claim directly scooped by prior work → major.
  • Flanked-on-several-sides positioning (novel in combination, not invention) overstated as invention → major.
  • Missing acknowledgment of a relevant near-neighbor → minor.

Demonstrate or drop

Each finding names the specific prior/concurrent work with its date and link, and the exact axis it covers. No "there is probably related work." Cap: 12, most severe first.

Read the full file on GitHub · 63 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 · 63 lines · 39 tokens per session scan A 0c656c95a595

Subscribe to this mod's changes

related-work-gaps is an agent published in the GitHub repository tasumermaf/the-adversary (2 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 39 tokens to every session and 712 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 2026-08-31.

Related

Other agents, from other repositories

integrity-verification-agent

Zero-tolerance academic integrity gatekeeper for alterlab-research-pipeline (Stage 2.5 pre-review + Stage 4.5 post-revision). Performs 100% verification of references, citations, data, originality, and claim faithfulness. Resolves every reference's EXISTENCE and metadata deterministically via…

AlterLab-IEU/AlterLab-Academic-Skills · 194 tokens

meta-analysis-agent

Designs and executes meta-analyses when quantitative synthesis is feasible, computing effect sizes, assessing heterogeneity, generating forest-plot data, planning subgroup and sensitivity analyses, and applying the GRADE framework; otherwise produces a structured narrative synthesis framework.

AlterLab-IEU/AlterLab-Academic-Skills · 53 tokens

citation-compliance-agent

Verifies all citations in the paper draft for format correctness, cross-references in-text citations against the reference list, checks DOIs and URLs, and auto-corrects detected errors for the selected citation style.

AlterLab-IEU/AlterLab-Academic-Skills · 47 tokens

draft-writer-agent

Writes the complete paper draft section-by-section, following the Structure Architect's outline and the Argument Builder's blueprint, weaving citations naturally into the narrative and handling revision rounds.

AlterLab-IEU/AlterLab-Academic-Skills · 38 tokens

structure-architect-agent

Selects the optimal paper structure, designs a detailed section-by-section outline, allocates word counts, and maps evidence to sections, producing the blueprint the draft writer follows.

AlterLab-IEU/AlterLab-Academic-Skills · 39 tokens

visualization-agent

Parses paper data and statistical results to generate publication-quality figure code in Python (matplotlib/seaborn) or R (ggplot2) formatted to APA 7.0 standards, producing accessible, colorblind-safe visualizations with captions, labels, and LaTeX inclusion code.

AlterLab-IEU/AlterLab-Academic-Skills · 62 tokens