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 flonat/flonat-research --skill latex-diffgit clone --depth 1 https://github.com/flonat/flonat-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/skills/flonat/flonat-research/latex-diff)<a href="https://agentmods.dev/skills/flonat/flonat-research/latex-diff"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/latex-diff/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/flonat/flonat-research/latex-diff"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/latex-diff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Tool Misuse · line 107 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 107 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00056 | $0.01969 |
| Opus 5.5 | $0.00022 | $0.00788 |
| Sonnet 5.5 | $0.00011 | $0.00394 |
| Haiku 4.5 | $0.00006 | $0.00197 |
Grade A, and why
latex-diff 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 28d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LaTeX Diff
Compare two versions of a LaTeX document and report what actually changed — text, equations, citations, labels/refs, section titles, macros, environments, file add/remove, and moves — each graded by severity. Wraps the
latexdiff-agentCLI (packages/latex-diff). Member of thelatex-*source/build family.
When to Use
- "What changed between these two versions of the paper?"
- Building an R&R "summary of changes" or a preprint vN→vN+1 changelog
- Focusing a re-review on the changes that matter (semantic-impact only)
- Sanity-checking a co-author's edits before merging
When NOT to Use
- Compiling a document →
latex - Prose quality / proofreading →
proofread - A raw line diff is enough →
git diff(this skill is LaTeX-aware: it knows a changed\citekey from a reflowed paragraph)
What it produces
Two views from the same canonical diff:
- Human summary — grouped by file and section, every line carrying a change
id, a severity badge, and afile:linelocation. - Machine-readable JSON — severity-graded
ChangeRecords.semantic_impact: trueflags the changes a reviewer should actually read.
For a persistent run inside a research project, these are the mandatory core files. Use one timestamp-only basename for the whole run:
reviews/<scope>/<check>/<YYYY-MM-DD-HHMM>.md
reviews/<scope>/<check>/<YYYY-MM-DD-HHMM>.changes.json
Here and below, <check> is this skill's frontmatter name.
Co-locate applicable typed companions with the same basename:
.full.json— unfiltered machine-readable inventory.changes.md— full or raw human-readable inventory when the primary report is a shorter curated summary.diff.texand.diff.pdf— rendered manuscript comparison.source.patch— exact source patch for source-only changes such as citation rekeys
The core pair is stable; companions vary with the comparison. Do not replace the core pair with a PDF, patch, or run-specific directory.
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.
- 28d ago Changed 383dc82fca65
- 1mo ago First seen · 176 lines · 56 tokens per session scan A 62e145a592a0
latex-diff is a skill published in the GitHub repository flonat/flonat-research (147 stars, last pushed 22d ago), licensed MIT. It adds 56 tokens to every session and 1,969 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
manuscript-as-code
Treat manuscripts as software: version control, reproducible builds, figure pipelines, CI, and structured repo layout. Helps teams avoid 'finalv7' chaos and ensures submission-ready artifacts.
commit
Analyze git diffs or staged changes and generate conventional commit messages that explain WHY a change was made. Supports auto-detecting type and scope, intelligent file staging, and interactive overrides. Use when asked to "write a commit message", "generate a commit", "describe my changes", "commit this"…
push-preflight
Secret-scans the commits a git push would send (gitleaks + regex layer; never history), then checks clean tree, forbidden files and fast-forward, with size and open-issue advisories. Refuses on any secret hit, no bypass. Triggers on: push to origin, push to github, push to remote, git push, can we push, safe to push…
tools
Utility commands — commit, compile, validate-bib, journal, context-status, deploy, learn. Replaces individual utility skills.
commit-push-pr
Commit changes, push to remote, and create a pull request. Use for completing features or fixes ready for review.
commit
Stage, commit, create PR, and merge to main. Use for the standard commit-PR-merge cycle.