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.
npx skills add dgilford/ai-science-toolkit --skill lit-reviewgit clone --depth 1 https://github.com/dgilford/ai-science-toolkitWrote 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/skills/dgilford/ai-science-toolkit/lit-review)<a href="https://agentmods.dev/skills/dgilford/ai-science-toolkit/lit-review"><img src="https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/lit-review/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/skills/dgilford/ai-science-toolkit/lit-review"><img src="https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/lit-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 7 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 46 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Supply Chain · line 55 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium Rogue Agent · line 4 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 55 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 77 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 77 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00049 | $0.01137 |
| Opus 5 | $0.00024 | $0.00568 |
| Sonnet 5 | $0.00010 | $0.00227 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade B, and why
lit-review scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
summary: 'Search and synthesize scientific literature from Zotero, arxiv, bioRxiv, Google Scholar, and Consensus. Zotero write support needs `ZOTERO_*` env vars in `~/.claude/settings.json`.' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://api.zotero.org/users/$ZOTERO_USER_ID/collections?limit=100" \ How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conduct a literature search and deliver a structured scientific briefing. See REFERENCE.md for mode-specific guidance.
On invocation, ask the user
- Topic — what are we searching for?
- Mode —
frame/methods/interpret/landscape/synthesize - Starting point (optional) — any known papers, authors, or search terms to seed from?
Search order
- Zotero — existing library first; note what's already there
- Consensus — synthesized search for landscape and key claims
- Google Scholar — seminal works, citation counts, author networks
- arxiv / bioRxiv — recent and unpublished work
Stop adding sources once coverage is sufficient for the mode.
Output structure
1. High-level summary — 1–2 paragraphs: what the field looks like, what is settled, what is contested. Tag findings as established / debated / emerging throughout.
2. Topical review — key ideas, findings, and debates organized by theme. Apply mode-specific guidance from REFERENCE.md. Distinguish what is well-established, actively debated, and absent.
3. Papers — for each paper:
- Full citation (authors, year, title, journal/venue)
- Peer-reviewed or preprint — flag explicitly
- Key contribution in 1–2 sentences
- Relevance to the current topic and mode
4. Offers — always prompt:
- Save to
REFERENCES.md? — check if it exists and show existing entries first. Append using the template in REFERENCE.md. Never overwrite. - Add to Zotero? — list papers not already in the library, then ask. If yes, execute the steps below.
Adding papers to Zotero
Required env vars (set in ~/.claude/settings.json → env block):
ZOTERO_USER_ID— your numeric Zotero user ID (find it at zotero.org/settings/keys)ZOTERO_API_KEY— a Zotero API key with write access (same page)ZOTERO_INBOX_COLLECTION— name of the collection to file new papers into (e.g.Inbox)
If any required var is unset, skip the Zotero write step and tell the user what to configure.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 84 lines · 49 tokens per session scan B 480861a27e5e
lit-review is a skill published in the GitHub repository dgilford/ai-science-toolkit (62 stars, last pushed 21d ago), licensed MIT. It adds 49 tokens to every session and 1,137 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
metforge-model-diagnose
Diagnose atmospheric-model and dynamical-core experiments. Use for idealized tests, balanced flow, hydrostatic rest, density currents, advection, gravity/acoustic waves, mountain waves, baroclinic instability, conservation and budget closure, error growth, convergence, timestep/resolution/domain/MPI sensitivity…
metforge-analysis
Perform reproducible atmospheric-science calculations and statistical diagnostics. Use when the agent needs to calculate established or custom climate indices, derive meteorological variables, compute trends, detrend or filter time series, perform EOF/PCA, regression, correlation, composites, bootstrap or significance…
metforge-data
Acquire and prepare atmospheric, climate, and Earth-system datasets reproducibly. Use when the agent needs to find an authoritative dataset, choose among ERA5/CMIP/GPM/MERRA-2/NOAA or similar products, download or subset NetCDF/GRIB/Zarr data, write CDS/Earthdata/ESGF/OPeNDAP acquisition code, inspect coordinates and…
metforge-figure
Design, create, revise, and audit atmospheric-science figures. Use for maps, map differences, vertical sections, Hovmöller diagrams, profiles, spectra, budgets, convergence plots, conservation/error-growth diagnostics, ensemble comparisons, and publication multi-panel figures from NetCDF/xarray or tabular data. Also…
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
epd-compare
Compare EPD products on normalized GWP and other impacts while checking declared units, system boundaries, and LEED eligibility. Use for side-by-side EPD comparison.