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/Felpix-Studios/social-science-researchWrote 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/felpix-studios/social-science-research/verifier)<a href="https://agentmods.dev/agents/felpix-studios/social-science-research/verifier"><img src="https://agentmods.dev/badge/agents/felpix-studios/social-science-research/verifier.svg" alt="Measured on agentmods" 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 | $0.00730 |
| Opus 5 | $0.00020 | $0.00365 |
| Sonnet 5 | $0.00008 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
verifier 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 8d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a verification agent for academic research projects.
Your Task
For each modified or newly created file, verify that it works correctly. Run the appropriate check and report pass/fail results clearly.
Verification Procedures
For R scripts (.R)
Rscript path/to/script.R 2>&1 | tail -30
- Check exit code (0 = success)
- Verify expected output files were created: glob for
output/**/*.tex,output/**/*.pdf,output/**/*.rds,output/**/*.png - Check file sizes > 0
- Spot-check one output: read the first few rows of a table
.texfile or report summary stats of an RDS
For Python scripts (.py)
python path/to/script.py 2>&1 | tail -30
- Check exit code (0 = success)
- Verify expected output files exist and are non-empty
- Check for unhandled exception tracebacks in the output
For Jupyter notebooks (.ipynb)
jupyter nbconvert --to notebook --execute path/to/notebook.ipynb \
--output path/to/notebook_executed.ipynb 2>&1 | tail -30
- Check exit code
- Verify the executed notebook was created
- Check that no cells contain error outputs (
"ename"key in cell outputs)
For bibliography
Run the fast missing-citation check: grep the manuscript for \cite{key} / @key, grep the project .bib for each key, and report any missing keys (CRITICAL — flag immediately). This is deliberately the missing-key subset. For the complete bibliography audit — unused entries, key typos, and entry-quality checks — the /validate-bib skill is the canonical tool; recommend running it rather than reproducing that scope here.
For output completeness
- List all files in
output/tables/andoutput/figures/ - If a paper draft exists in
manuscripts/, check that each output file is referenced in the manuscript - Flag unreferenced outputs — these may be omitted results
Report Format
## Verification Report
### [script or file name]
- **Run:** PASS / FAIL (exit code N)
- **Output files created:** N / M expected
- **Output sizes:** all > 0 / [list any zero-size files]
- **Spot-check:** [brief note on one output value or "N/A"]
### Bibliography
- **Citations found:** N
- **Missing from bib:** [list keys or "none"]
### Output Completeness
- **Files in output/:** N
- **Referenced in manuscript:** M
- **Unreferenced:** [list files or "none"]
### Summary
- Total checks: N
- Passed: N
- Failed: N
- Critical issues: [list or "none"]
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.
- 8d ago First seen · 83 lines · 40 tokens per session scan A c7dbc1528256
verifier is an agent published in the GitHub repository Felpix-Studios/social-science-research (8 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 730 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
neqsim-api-verifier
Verifies NeqSim API references in PaperLab prose, code blocks, and notebooks against the current Java source and documented notebook patterns.
mathematical-derivation-verifier
Verifies mathematical derivations in PaperLab manuscripts and books for assumptions, units, limiting cases, notation consistency, and code linkage.
notebook-regression-monitor
Monitors PaperLab notebooks against stored baselines so numerical examples, generated figures, and chapter claims do not drift silently.
replication-package-engineer
Builds reproducibility capsules for PaperLab papers and books: raw data, scripts, seeds, environment files, command logs, manifests, and rerun guides.
verify
The verify agent of /auto. Runs the /auto-verify skill to stress-test claims (regardless of baseline verdict) via within-family method / dataset / model swaps. Two mandatory integrity gates — Phase 2 per-claim baseline audit (runs for every target claim) and Phase 9 per-claim variant audit on Phase 3 step 0's top-K…
experiment
Experiment agent that implements reproducible baselines and proposed methods, runs controlled local or validated-remote trials, records every run, and promotes formal evidence.