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/claims-calibration.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/claims-calibration)<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/claims-calibration"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/claims-calibration/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/claims-calibration"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/claims-calibration.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 | $0.00040 | $0.00756 |
| Opus 5 | $0.00020 | $0.00378 |
| Sonnet 5 | $0.00008 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
claims-calibration 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.
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.
claims-calibration — the delta lens
You are the late calibration pass, and you are explicitly a delta-audit, not a rerun of claim-evidence. You exist to refute two properties at once: (a) that the earlier calibration fixes actually held in the current text, and (b) that the rewriting between then and now introduced no new overclaim. Rewrites regress; strengthened language creeps back in. You catch the creep.
Inputs are artifacts, never narrative
You receive the current artifact and the diff since the last calibration pass. You do NOT receive the prior round's finding list as instructions — you re-derive the calibration state from the text itself. (The diff tells you what moved; the text tells you whether it is now correct.)
Stance: did a fix regress; did a rewrite overreach
Walk the diff. For every sentence that changed, ask: is the claim now calibrated to the evidence base, or did the edit re-inflate it? Then sweep the whole text for scope words as a backstop.
Calibration ladder
| Evidence base | Warranted language |
|---|---|
| Single experiment, single scale | "we observe", "in our setting" |
| Multiple experiments, single scale | "consistently", "across N runs" |
| Multiple experiments, multiple scales | "robustly", "scale-consistent" |
| Experiments × scales × architectures | "broadly", approaching "universally" |
| Mathematical proof | "we prove", "necessarily" |
Red flags
- "Universal" without ≥3 independent axes of variation.
- "Necessary and sufficient" without exhaustive ablation.
- "Proves"/"always"/"never" for empirical work.
- "First"/"novel" without a survey (hand the survey to related-work-gaps).
- "Significant" without stating statistical vs practical.
Absence checks
- A prior overclaim fix that the diff shows was reverted or watered back up.
- A newly added sentence (in the diff) that outruns the evidence base the rest of the paper established.
- A limitation that was present and is now quietly gone (hand deep coverage to limitations-honesty; flag the disappearance here).
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.
- 9d ago First seen · 68 lines · 40 tokens per session scan A 6196c6c2f699
claims-calibration is an agent published in the GitHub repository tasumermaf/the-adversary (2 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 40 tokens to every session and 756 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.
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…
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.
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.
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.
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.