Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/roomi-fields/paper-trailWrote 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/commands/roomi-fields/paper-trail/paper-trail-receipts)<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-receipts"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-receipts/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/commands/roomi-fields/paper-trail/paper-trail-receipts"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-receipts.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 | $0.00415 |
| Opus 5 | $0.00020 | $0.00208 |
| Sonnet 5 | $0.00008 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
paper-trail-receipts 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 10d 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.
What it actually says
/paper-trail:receipts — Local audit only (no remote API)
Variant of /paper-trail:audit-article that operates only on local
data (registry + PDFs on disk). No paper-search MCP calls, no
WebSearch, no Crossref API.
Usage
/paper-trail:receipts <path-to-paper.tex>
/paper-trail:receipts <path-to-paper.md>
No --warn mode here (use /paper-trail:audit-article --warn if you
want inline warnings).
What it does
Same as audit-article but :
- Skips UNVERIFIABLE escalation : if a cited ref isn't in the registry or its PDF isn't on disk, the verdict is UNVERIFIABLE without further investigation
- No remote search : doesn't try to fetch missing PDFs via cascade
- No metadata enrichment : doesn't cross-check author/year via Crossref
Useful when :
- You're offline
- You want a fast first-pass audit (~10s for 20 citations)
- You want to verify the claims against PDFs you already have, without triggering acquisition of missing ones
Output
RECEIPTS.md with the same format as audit-article.
Citations with no local PDF will be marked UNVERIFIABLE (no local PDF, run /paper-trail:cascade <slug> to acquire).
Cross-reference
/paper-trail:audit-article— full audit with remote enrichment/paper-trail:cascade <slug>— acquire missing PDFs/paper-trail:audit-sota— bibliography-level audit (no per-claim verification)
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.
- 10d ago First seen · 53 lines · 40 tokens per session scan A fdb162eb97f5
paper-trail-receipts is a command published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 415 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 commands, from other repositories
lit-landscape
Generate figures visualizing literature trends, citation patterns, and research gaps.
verify-citations
Verify all citations against bibliography.
lit-review
A command for carrying out a systematic literature review, meaning a structured search and summary of research papers on a chosen topic. It also builds a citation graph showing connections between papers.
proof-readability
Improve the exposition and readability of a mathematical proof already verified as correct without changing its mathematics. Use when polishing a lemma, theorem, proof, or appendix after correctness checks. Not for verifying the proof; use $verify-math.
causal-design
Design or audit the identification strategy for an observational study. Use when the task concerns estimands, causal assumptions, threats to identification, or defensible research design rather than model implementation.
cite-check
Verify that citations actually exist and that the claims they support are faithful to the cited source. Runs deterministic existence checks (Crossref / OpenAlex / Semantic Scholar / arXiv) plus a claim-faithfulness pass via the alterlab-citation-verifier skill.