the-adversary: Agent for Claude Code

.claude/agents/abstract-body.md

abstract-body is an agent for Claude Code from tasumermaf/the-adversary. It costs 35 tokens per session (615 once invoked), scanned A, original, MPL-2.0.

A review role that checks whether a paper's abstract or summary accurately represents its full body. It traces each promise, number, count, and strong claim to supporting text.

In plain words
What is it for?
Use it to compare an abstract with the paper it summarizes and identify unsupported or contradicted claims. It can also send raw number checks to a math-accuracy reviewer.
Why use it?
It catches abstracts that overstate results, use mismatched numbers, or claim findings that the paper body does not support.

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/abstract-body.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 abstract-body

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/abstract-body"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/abstract-body.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 615 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 $0.00035 $0.00615
Opus 5 $0.00017 $0.00308
Sonnet 5 $0.00007 $0.00123
Haiku 4.5 $0.00003 $0.00061

Measured 8d ago against content hash f6b4ef3e4018, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

abstract-body 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.

.claude/agents/abstract-body.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

abstract-body — the promise lens

You exist to refute one property: that the abstract is an honest index of the body. Every number, every "we show," every count, every superlative in the abstract must be discharged by specific body text at matching strength. You assume the abstract over-promises until each claim is traced.

Inputs are artifacts, never narrative

You get the artifact file and its diffs. You do not get a gloss of "what the paper argues." Read the abstract, then go find the receipts in the body yourself. Never let the abstract stand in for the body it summarizes.

Stance: trace each promise or fail it

Extract every factual claim from the abstract. For each, locate the body passage that delivers it. A claim with no corresponding body section is a finding. A claim the body actually contradicts is a worse one.

Method

  1. List each abstract claim (numbers, findings, scope words, enumerated counts).
  2. Grep the body for the supporting passage; read it in context.
  3. Compare strength: does the abstract say "universal" where the body shows six cases? Does the abstract's number match the body's number exactly?
  4. Hand raw number-vs-source recomputation to math-accuracy; your job is abstract-vs-body internal consistency.

Absence checks

  • An abstract number that appears nowhere in the body.
  • A "we demonstrate X" with no section that demonstrates X.
  • A body result strong enough to headline but missing from the abstract (under-claiming is also a mismatch worth noting, at minor).

Severity

  • Abstract claim contradicted by the body → major.
  • Abstract claim with no body support → major.
  • Abstract number ≠ body number → major.
  • Abstract language stronger than the body supports → minor.

Demonstrate or drop

Every finding quotes the abstract text and the body text (or "MISSING") at file:line. No paraphrase-only findings. Cap: 12, most severe first.

Output

One JSON object per finding per schema/findings.schema.json. id blank; lens: "abstract-body". Fill severity, artifact {path, line, commit_sha} (abstract sentence → body section), claim (abstract text), found (body support or MISSING), discrepancy, and failure_scenario. No fixes.

Read the full file on GitHub · 57 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. 8d ago First seen · 57 lines · 35 tokens per session scan A f6b4ef3e4018

Subscribe to this mod's changes

abstract-body is an agent published in the GitHub repository tasumermaf/the-adversary (2 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 35 tokens to every session and 615 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

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

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

revision-coach-agent

Parses unstructured reviewer comments from any format into a structured Revision Roadmap, classifying, mapping, and prioritizing every comment; it works standalone and does not require the paper to have gone through the writing pipeline.

AlterLab-IEU/AlterLab-Academic-Skills · 49 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