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/ghqqqq/codex-overleaf-link/parallel-subagentsnpx skills add Ghqqqq/codex-overleaf-link --skill parallel-subagentsgit clone --depth 1 https://github.com/Ghqqqq/codex-overleaf-linkWrote 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/ghqqqq/codex-overleaf-link/parallel-subagents)<a href="https://agentmods.dev/skills/ghqqqq/codex-overleaf-link/parallel-subagents"><img src="https://agentmods.dev/badge/skills/ghqqqq/codex-overleaf-link/parallel-subagents.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 | $0.00092 | $0.01709 |
| Opus 5 | $0.00046 | $0.00855 |
| Sonnet 5 | $0.00018 | $0.00342 |
| Haiku 4.5 | $0.00009 | $0.00171 |
Grade A, and why
parallel-subagents 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Subagents
The native host can run parallel Codex workers for you. You cannot spawn processes yourself (the sandbox forbids it) — instead you write job files into a queue directory and poll for result files. Each worker is a full Codex agent confined to the files you assign it.
1. When to use
Use this when ALL of these hold:
- The task splits into ≥ 2 independent slices: different files, or different sections of one file (use the scatter-gather workflow in §5).
- Slices do not depend on each other's output.
- Each slice is small enough to finish in a few minutes.
Do NOT use it (work sequentially yourself instead) when:
- Slices are deeply cross-referenced and must be edited together.
- There are fewer than 2 real slices.
- The handshake file below is missing or not
ready.
1b. Explicit scope — the iron rule
Every job's task MUST state its exact working scope, and scopes MUST NOT
overlap:
- multi-file job: name the file(s) and what inside them is in scope;
- single-file slice job: name the section (
\section{...}title) and quote the slice's exact first and last source lines. Never write two jobs whose scopes could touch the same text. If you cannot state a slice's boundaries precisely, do that slice yourself instead.
2. Handshake
Read .codex-overleaf-subagents/broker.json. If it is missing or its
status is not ready, the broker is off — do everything yourself. Respect
maxWorkers, maxJobsPerRun, and perWorkerTimeoutMs (size each job to
finish well inside it).
3. Write jobs
One job per slice. Each job OWNS its files exclusively — no file may appear
in two jobs. Write atomically: create a temp file, then mv it to its final
.json name.
cat > .codex-overleaf-subagents/jobs/.tmp-ch3 <<'JSON'
{
"id": "ch3",
"title": "Polish chapter 3",
"task": "Polish sections/ch3.tex for grammar, flow, and concision. Keep all math and citations intact. Follow the shared style notes: <paste the style guidance here>.",
"files": ["sections/ch3.tex"],
"readOnlyContext": ["main.tex", "macros.tex"]
}
JSON
mv .codex-overleaf-subagents/jobs/.tmp-ch3 .codex-overleaf-subagents/jobs/ch3.json
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 · 156 lines · 92 tokens per session scan A f60a6f754dfb
parallel-subagents is a skill published in the GitHub repository Ghqqqq/codex-overleaf-link (76 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,709 once invoked, about $0.0005 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
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
systems-paper-writing
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
paperjury
Three modes for CS-conference papers (CVPR/ICCV/ECCV vision, ACL/EMNLP/NAACL NLP, ICLR/NeurIPS/ICML/AAAI ML). DIRECT-EDIT mode (common): the user describes a change in Chinese or English and the manuscript (LaTeX or Markdown) is edited directly through a CS-venue writing toolkit with author sign-off (use for 改这段 /…
overleaf
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
chrome-extension
Use when building or shipping a Manifest V3 browser extension and hitting its quirks — service worker dying and losing state, permission warnings, a Chrome Web Store rejection, content-script/worker/popup messaging, or an MV2-to-V3 migration. NOT a generic web app (that is nextjs), NOT a desktop shell (that is…