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 agentmods add skills/fcakyon/phd-skills/comparenpx skills add fcakyon/phd-skills --skill comparegit clone --depth 1 https://github.com/fcakyon/phd-skillsWrote 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/fcakyon/phd-skills/compare)<a href="https://agentmods.dev/skills/fcakyon/phd-skills/compare"><img src="https://agentmods.dev/badge/skills/fcakyon/phd-skills/compare.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 | $0.00082 | $0.01161 |
| Opus 5 | $0.00041 | $0.00580 |
| Sonnet 5 | $0.00016 | $0.00232 |
| Haiku 4.5 | $0.00008 | $0.00116 |
Grade A, and why
compare 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 5d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compare: same-epoch run comparison across trackers
The most common comparison error is reporting "run A is 4 percentage points behind baseline" when run A is at epoch 11 of 100 and the baseline number is from epoch 100. The student is still training; the comparison is meaningless. This skill enforces same-epoch alignment.
The agentic Stop hook routes here from reason when an assistant reports a delta without aligning the runs.
When to run
The user just said any of:
- "compare run A to baseline / to run B"
- "is my run improving / catching up / falling behind"
- "rank these experiments"
- "X vs Y wandb / neptune"
- "track lag against baseline"
Auto-detect the tracker
Check in this order:
WANDB_API_KEYenv var set, orwandbimports in the project → wandbNEPTUNE_API_TOKENenv var set → neptuneMLFLOW_TRACKING_URIenv var set, ormlruns/dir present → mlflowruns/orlightning_logs/dir present → tensorboard*results*.json/*meta*.jsonfiles in run dirs → local file format
If none, ask the user where metrics live before guessing.
The protocol
1. Identify the runs
Get full names (no shortcodes). If the user says "fvs-fm vs the baseline", clarify:
- which
fvs-fmrun (project + entity + run-id) - which baseline (full run name; baselines often have several variants)
2. Fetch metric history (not just final value)
You need the full curve, not the last reported value. Final-value-only comparisons hide convergence dynamics.
For wandb:
import wandb
api = wandb.Api()
run = api.run("entity/project/run-id")
history = run.history(samples=10000) # full history, not just summary
For tensorboard, parse the event files (tensorboard.backend.event_processing.event_accumulator.EventAccumulator).
For neptune / mlflow, use their respective APIs.
3. Find the student's current step
The student is the run still in progress (or the one being evaluated). Get its current epoch / step from the latest history row.
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.
- 5d ago First seen · 103 lines · 82 tokens per session scan A 0803684f116c
compare is a skill published in the GitHub repository fcakyon/phd-skills (382 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,161 once invoked, about $0.0004 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
literature-review
Write a comprehensive, structured literature review on a topic. Searches the literature via Corbis, organizes into thematic strands, writes synthesized prose (not paper-by-paper enumeration), and outputs as Markdown, LaTeX section, or standalone LaTeX document with proper BibTeX citations.
literature-landscape
Generate figures that visualize patterns in an academic literature: publication trends, citation landmarks, journal distributions, thematic evolution, method timelines, and coverage gap maps. Uses Corbis search data and Python/matplotlib.
literature-positioning-map
Map the closest literature and sharpen contribution claims for finance or real-estate papers. Use for related-literature sections, novelty maps, and closest-paper comparisons.
verify-citations
Audit citations in LaTeX files -- check all \cite keys exist in .bib and verify via literature search.
finance-idea-screening
Screen and refine research ideas in corporate finance, investments, asset pricing, and real estate. Use for brainstorming, novelty checks, contribution framing, and journal-fit triage.
research-idea-generator
Generate novel research ideas in finance and real estate using structured heuristic lenses with internal rejection filtering. Produces a curated Idea Menu of survivors, not a brainstorming list.