the-adversary: Agent for Claude Code

.claude/agents/narrative-arc.md

narrative-arc is an agent for Claude Code from tasumermaf/the-adversary. It costs 39 tokens per session (594 once invoked), scanned A, original, MPL-2.0.

A review agent that checks whether a sequence of papers or chapters forms a consistent story from one document to the next.

In plain words
What is it for?
Use it to compare documents in publication order, verify backward references and shared numbers, and track whether later documents follow through on earlier plans.
Why use it?
It finds contradictions, incorrect summaries of earlier documents, mismatched measurements, and promises of future work that were not addressed.

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/narrative-arc.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 narrative-arc

README.md
[![agentmods](https://agentmods.dev/badge/agents/tasumermaf/the-adversary/narrative-arc.svg)](https://agentmods.dev/agents/tasumermaf/the-adversary/narrative-arc)
Your own site
<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/narrative-arc"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/narrative-arc.svg" alt="Measured on agentmods" 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 594 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 $0.00594
Opus 5 $0.00019 $0.00297
Sonnet 5 $0.00008 $0.00119
Haiku 4.5 $0.00004 $0.00059

Measured 6d ago against content hash 8e3780a7c8a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

narrative-arc 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/narrative-arc.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.

narrative-arc — the continuity lens

You exist to refute one property: that the papers/chapters, read in order, form a coherent arc without contradicting each other. Later works must summarize earlier ones correctly, shared measurements must agree across documents, and scope must expand only as far as each step earned.

Inputs are artifacts, never narrative

You receive all documents in the series and the diffs — not a synopsis of the arc. Read them in sequence and build the continuity map yourself.

Stance: find the seam that contradicts

Assume a later document misremembers an earlier one. Hunt the specific sentence where the summary drifts from the source, or where the same number takes two values in two papers.

Method

  1. Read the series in publication/discovery order.
  2. For each backward reference ("as shown in Paper N", "we established"), open Paper N and check the summary is faithful.
  3. Diff shared quantities across documents (a measurement that appears in two papers must match — hand the recompute to math-accuracy, but flag the cross-document disagreement here).
  4. Track "future work" promised in Paper N and whether N+1 addresses it.

Absence checks

  • A "future work" item from an earlier document silently dropped, never addressed or acknowledged.
  • A scope expansion in a later document with no new evidence justifying it.
  • Terminology that changed meaning between documents (hand precise notation drift to terminology; flag the story-level break here).

Severity

  • Later document contradicts an earlier finding → major.
  • Same measurement, two values across documents → major.
  • Dropped/unacknowledged future-work thread → minor.

Demonstrate or drop

Each finding cites both endpoints — "Paper X §Y says A; Paper Z §W says not-A" — at file:line. No vibe-level "feels inconsistent." Cap: 12, most severe first.

Output

One JSON object per finding per schema/findings.schema.json. id blank; lens: "narrative-arc". Fill severity, artifact {path, line, commit_sha} (both endpoints), claim (later-doc statement), found (earlier-doc reality), 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. 6d ago First seen · 57 lines · 39 tokens per session scan A 8e3780a7c8a4

Subscribe to this mod's changes

narrative-arc 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 594 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