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 MattArtzAnthro/gephi-ai --skill verify-claimgit clone --depth 1 https://github.com/MattArtzAnthro/gephi-aiWrote 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/mattartzanthro/gephi-ai/verify-claim)<a href="https://agentmods.dev/skills/mattartzanthro/gephi-ai/verify-claim"><img src="https://agentmods.dev/badge/skills/mattartzanthro/gephi-ai/verify-claim/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/mattartzanthro/gephi-ai/verify-claim"><img src="https://agentmods.dev/badge/skills/mattartzanthro/gephi-ai/verify-claim.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 | $0.00054 | $0.00570 |
| Opus 5 | $0.00027 | $0.00285 |
| Sonnet 5 | $0.00011 | $0.00114 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
verify-claim 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify a Structural Claim
Verify one claim against the live graph. Independence is the point: do not try to make the claim true; determine whether the graph supports it.
Read ../gephi/references/claim-verification.md before choosing the method. If
the user did not provide a claim, ask for it in one sentence.
Workflow
- Call
gephi_health_check. If it fails, tell the user to start Gephi and stop. - Preserve the claim verbatim and classify it as comparison, connectivity, centrality, grouping, or robustness.
- Match the measurement to the claim's words:
- comparison, such as "X is more central than Y": compute the named metric,
then call
gephi_compare_nodes; - connectivity: use
gephi_visual_qawith the claimed grouping or count cross-group edges with a read-only filter; - importance: compute the metric the word implies—bridge means betweenness, reach may mean degree or PageRank—and rank the relevant nodes;
- robustness: call
gephi_whatif, which edits and deletes a scratch workspace while leaving the real graph unchanged.
- comparison, such as "X is more central than Y": compute the named metric,
then call
- If the claim is vague, measure the two or three plausible meanings and report them separately. Do not silently choose the result most favorable to the claim.
- Choose exactly one verdict:
confirmed,refuted, orcan't-tell.
Guardrails
- Give the actual number, not just a verdict.
- Never turn
can't-tellintorefuted. - Flag small or skewed samples even when the measured result is confirmed.
- Computing statistic columns is allowed; recoloring, relayout, destructive filtering, and graph edits are not.
- Never assert scale-free or power-law structure from a heavy tail.
Verified Record
Call gephi_claim_record with the verbatim claim, classification, verdict,
metric or node column, every supporting node ID, the values read for those nodes,
other numeric evidence, the caveat, and an export path when requested. The tool
re-reads the live graph and checks the receipts.
If the result says verified: false, remeasure and call it again. Do not present
unverified numbers as checked.
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 · 54 tokens per session scan A a6c263db038e
verify-claim is a skill published in the GitHub repository MattArtzAnthro/gephi-ai (22 stars, last pushed 8d ago), licensed Apache-2.0. It adds 54 tokens to every session and 570 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
earth2studio-create-datasource
Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.
earth2studio-data-fetch
Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.
i4h-catheter-navigation
Overview of workflows/catheternavigation/ (fluorosim DRR, XPBD physics, vasculature digital twin). Use when the user asks what the catheter navigation workflow is, what's supported, or where to start.
i4h-workflow-dataset-convert
Convert workflow HDF5 recordings to LeRobot datasets for training or browser inspection. Use for conversion; do not use for replay, augmentation, or raw-data repair.
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.