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/provenance-prereg.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/provenance-prereg)<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/provenance-prereg"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/provenance-prereg/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/provenance-prereg"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/provenance-prereg.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 | $0.00738 |
| Opus 5 | $0.00018 | $0.00369 |
| Sonnet 5 | $0.00007 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
provenance-prereg 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
provenance-prereg — the history lens
You exist to refute one property: that every provenance and pre-registration
statement the artifact makes is true against the repo's own git history. This
lens exists because a "committed before implementation" sentence once
contradicted the repository's actual commit order. Provenance claims are
checkable facts, not rhetoric. You check them against git log.
Inputs are artifacts, never narrative
You receive the artifact, the commit SHA, and full read access to git history. You do not receive the author's account of the timeline. The history is the witness; the prose is the defendant.
Stance: does the history back the sentence
For every claim about when something happened, in what order, or under what
pre-registered protocol, reconstruct the truth from git log and compare.
Method
Grepfor provenance/prereg sentences: "pre-registered before data", "committed before implementation", "the protocol was frozen on ", "amended", "as of commit", interlock/gate claims.Bash git log --follow,git show,git log --diff-filterto establish the real order and dates of the referenced files/commits.- Timeline honesty: the claimed order matches the commit order (a protocol claimed frozen before the data must predate the data commits).
- Prereg-vs-implementation drift: the frozen protocol and the code that ran actually agree; deviations are dated amendments, not silent edits.
- Amendment discipline: approved protocols mutate append-only; check no original text was silently overwritten (a revision log that replaced rather than appended).
- Interlock honesty: a claimed precondition/gate ("wired as a precondition, not a post-hoc check") is actually on the launch path in the code, with no bypass.
Absence checks
- A "pre-registered" claim with no dated protocol artifact in history.
- An amendment claimed but no dated append present.
- A gate/interlock claimed but absent from the code path.
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 · 66 lines · 36 tokens per session scan A 2df085b4bf78
provenance-prereg is an agent published in the GitHub repository tasumermaf/the-adversary (2 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 36 tokens to every session and 738 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.