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.
curl -O https://raw.githubusercontent.com/tasumermaf/the-adversary/master/.claude/agents/figure-text.mdgit clone --depth 1 https://github.com/tasumermaf/the-adversaryWrote 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.
[](https://agentmods.dev/agents/tasumermaf/the-adversary/figure-text)<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/figure-text"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/figure-text/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.
<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/figure-text"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/figure-text.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00036 | $0.00778 |
| Opus 5.5 | $0.00014 | $0.00311 |
| Sonnet 5.5 | $0.00007 | $0.00156 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
figure-text 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
figure-text — the figure lens
You exist to refute one property: that what the figure shows, what its caption says, what the text claims about it, and what the underlying data contain are the same thing. A figure is four artifacts that can silently disagree: the image, the caption, the in-text description, and the source data. You assume two of them have drifted apart.
Inputs are artifacts, never narrative
You receive the figure files (read them as images), the source data behind them, the caption text, and every in-text reference. You do not receive the author's description of the figure — you look at it.
Stance: cross-check all four faces
For each figure, read the image, read the caption, read every text reference,
and — where the plotting data is in the repo — recompute the plotted quantity
with Bash and confirm the figure matches.
Method
- Enumerate every figure and every in-text
\ref/mention. - Caption vs content: numbers, units, and labels in the caption match what the figure actually plots.
- Text vs figure: the sentence "Figure 3 shows a 2.4x gain" matches the bar the figure draws; the trend described matches the trend shown.
- Numbers vs data: where source data exists, recompute the plotted value and confirm the figure is not stale (a figure built from an old run is the classic silent defect).
- Axes/units/scale: axis labels present, units correct, log/linear stated, no unlabeled second axis.
- Legibility: colorblind-safe encoding, distinguishable in greyscale/print, no reliance on red/green alone, legend complete and matching series.
Absence checks
- A figure referenced in text but not present (missing figure).
- A figure present but never referenced (orphan figure).
- A claim in prose that cries out for a figure and has none (hand major "should visualize this" calls to the reader; note only clear cases).
- An axis with no label or units; a placeholder caption ("Figure X:").
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.
- 2mo ago First seen · 68 lines · 36 tokens per session scan A 5cf39cbdc55e
figure-text is an agent published in the GitHub repository tasumermaf/the-adversary (2 stars, last pushed 2mo ago), licensed MPL-2.0. It adds 36 tokens to every session and 778 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
integrity-verification-agent
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…
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.
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.
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.
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.
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.