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 Mexregkan/claude-for-researchers --skill sync-briefgit clone --depth 1 https://github.com/Mexregkan/claude-for-researchersWrote 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/mexregkan/claude-for-researchers/sync-brief)<a href="https://agentmods.dev/skills/mexregkan/claude-for-researchers/sync-brief"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/sync-brief/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/mexregkan/claude-for-researchers/sync-brief"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/sync-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00437 |
| Opus 5 | $0.00000 | $0.00218 |
| Sonnet 5 | $0.00000 | $0.00087 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
sync-brief 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 12d 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.
What it actually says
sync-brief
Propagate load-bearing changes from workbook.tex to brief.tex.
When to invoke
After establishing a new result, correcting a formula, or completing a section in workbook.tex. NOT for every edit — only for changes that affect what is established.
What "load-bearing" means
Propagate:
- New theorem or proposition (statement, not proof)
- Corrected formula (sign flip, wrong prefactor, wrong argument)
- New result about the mathematical structure (new pole, new residue value, etc.)
- Change to a key definition
- A claim moved from "open" to "established" (or vice versa)
Do NOT propagate:
- Pedagogical re-derivations of existing results
- Reorganization / renaming without content change
- Summary and outlook subsections
- Typo fixes
When in doubt, ask the user.
Steps
-
Identify the change. Ask the user what changed, or run
git diff workbook.texto see recent edits. -
Classify. Apply the load-bearing filter above. If ambiguous, ask.
-
Locate the corresponding section in brief.tex. Grep for a related label, theorem name, or keyword. Do NOT read brief.tex in full.
-
Make the targeted edit. In brief.tex:
- Add the new theorem statement (without proof)
- Replace the old formula with the corrected one
- Update the "Status" line (ESTABLISHED / OPEN / CORRECTED)
- Add a cross-reference to the workbook.tex section label
-
Compile brief.tex (use
/latex-compile brief.tex). -
Report:
- What was propagated (which result, from which section)
- What was deemed not load-bearing and skipped
- Compilation status
Output format
Propagated: [result name] from sec:[label] → brief.tex §N (eq. [label])
Skipped (not load-bearing): [what and why]
brief.tex: M pages, clean.
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.
- 12d ago First seen · 55 lines · 0 tokens per session scan A 23158e1f701c
sync-brief is a skill published in the GitHub repository Mexregkan/claude-for-researchers (52 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 437 tokens. 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
latex
Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality. Use when a .tex source must be built or a concrete compilation failure repaired. Not for corpus-wide build checks, visual polish after a clean build, or creating a project; use $latex-health-check, $latex-polish, or…
beamer-deck
Create an academic presentation as a LaTeX Beamer source and reviewed PDF with an original theme. Use when the requested deliverable is a conference, seminar, or lecture deck in Beamer. Not for PowerPoint or RevealJS; use $pptx or $quarto-deck.
bib-parse
Extract citations from a PDF and generate a validated .bib file. Use when the user asks to extract citations from a PDF and generate a validated .bib file. Reads the PDF, identifies referenced works, constructs BibTeX entries, and verifies metadata.
latex-template
Compare a project's LaTeX preamble and conventions against the canonical working-paper template. Use when diagnosing template drift without converting venue formats or editing prose.
review-response
Systematic reviewer response workflow: parse comments, classify by severity, develop response strategy, write structured rebuttal. Use when asked to 'write rebuttal', 'respond to reviewers', 'draft review response', or 'handle R&R'.
latex-health-check
Compile all LaTeX projects and report cross-project build consistency. Use when checking whether a collection of papers builds cleanly. Not for rendered visual inspection after a clean build; use $latex-polish.