Hermes Agent is an AI assistant that learns from its use by creating and improving skills, retaining knowledge, searching past conversations, and adapting to its users. It is for people who want to run an agent through a terminal or messaging platforms while connecting it to different AI models and scheduled tasks.
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 NousResearch/hermes-agent --skill research-paper-writinggit clone --depth 1 https://github.com/NousResearch/hermes-agentWrote 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/nousresearch/hermes-agent/research-paper-writing)<a href="https://agentmods.dev/skills/nousresearch/hermes-agent/research-paper-writing"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/research-paper-writing/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/nousresearch/hermes-agent/research-paper-writing"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/research-paper-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 7 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 YARA Match · line 4 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 25 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 45 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium MCP Rug Pull · line 274 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 479 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 1390 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 1625 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00022 | $0.16698 |
| Opus 5 | $0.00011 | $0.08349 |
| Sonnet 5 | $0.00004 | $0.03340 |
| Haiku 4.5 | $0.00002 | $0.01670 |
Grade C, and why
research-paper-writing scanned grade C with 2 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 8d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- ascii-guard-ignore --> Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.get( Copies of this mod
8 near-identical copies found in the catalogue:
- research-paper-writing — 100% identical, 0 lines differ
- research-paper-writing — 100% identical, 2 lines differ
- research-paper-writing — 91% identical, 554 lines differ
- research-paper-writing — 91% identical, 560 lines differ
- research-paper-writing — 91% identical, 548 lines differ
- research-paper-writing — 89% identical, 532 lines differ
- research-paper-writing — 89% identical, 532 lines differ
- research-paper-writing — 89% identical, 538 lines differ
How it starts
The opening of the file, as written. The whole thing — 1,628 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Paper Writing Pipeline
End-to-end pipeline for producing publication-ready ML/AI research papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, and COLM. This skill covers the full research lifecycle: experiment design, execution, monitoring, analysis, paper writing, review, revision, and submission.
This is not a linear pipeline — it is an iterative loop. Results trigger new experiments. Reviews trigger new analysis. The agent must handle these feedback loops.
┌─────────────────────────────────────────────────────────────┐
│ RESEARCH PAPER PIPELINE │
│ │
│ Phase 0: Project Setup ──► Phase 1: Literature Review │
│ │ │ │
│ ▼ ▼ │
│ Phase 2: Experiment Phase 5: Paper Drafting ◄──┐ │
│ Design │ │ │
│ │ ▼ │ │
│ ▼ Phase 6: Self-Review │ │
│ Phase 3: Execution & & Revision ──────────┘ │
│ Monitoring │ │
│ │ ▼ │
│ ▼ Phase 7: Submission │
│ Phase 4: Analysis ─────► (feeds back to Phase 2 or 5) │
│ │
└─────────────────────────────────────────────────────────────┘
When To Use This Skill
Use this skill when:
- Starting a new research paper from an existing codebase or idea
- Designing and running experiments to support paper claims
- Writing or revising any section of a research paper
- Preparing for submission to a specific conference or workshop
- Responding to reviews with additional experiments or revisions
- Converting a paper between conference formats
- Writing non-empirical papers — theory, survey, benchmark, or position papers (see Paper Types Beyond Empirical ML)
- Designing human evaluations for NLP, HCI, or alignment research
- Preparing post-acceptance deliverables — posters, talks, code releases
What ships with it
55 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/autoreason-methodology.md 19 KB
- references/checklists.md 13 KB
- references/citation-workflow.md 15 KB
- references/experiment-patterns.md 25 KB
- references/human-evaluation.md 18 KB
- references/paper-types.md 16 KB
- references/phase5-paper-drafting.md 31 KB
- references/reviewer-guidelines.md 13 KB
- references/sources.md 9.2 KB
- references/writing-guide.md 16 KB
- templates/aaai2026/aaai2026-unified-supp.tex 4.4 KB
- templates/aaai2026/aaai2026-unified-template.tex 62 KB
- templates/aaai2026/aaai2026.bib 4.7 KB
- templates/aaai2026/aaai2026.bst 29 KB
- templates/aaai2026/aaai2026.sty 12 KB
- templates/aaai2026/README.md 18 KB
- templates/acl/acl_latex.tex 14 KB
- templates/acl/acl_lualatex.tex 3.0 KB
- templates/acl/acl_natbib.bst 44 KB
- templates/acl/acl.sty 11 KB
- templates/acl/anthology.bib.txt 1.1 KB
- templates/acl/custom.bib 2.0 KB
- templates/acl/formatting.md 18 KB
- templates/acl/README.md 2.1 KB
- templates/colm2025/colm2025_conference.bib 496 B
- templates/colm2025/colm2025_conference.bst 26 KB
- templates/colm2025/colm2025_conference.pdf 120 KB
- templates/colm2025/colm2025_conference.sty 7.5 KB
- templates/colm2025/colm2025_conference.tex 13 KB
- templates/colm2025/fancyhdr.sty 20 KB
- templates/colm2025/math_commands.tex 12 KB
- templates/colm2025/natbib.sty 44 KB
- templates/colm2025/README.md 51 B
- templates/iclr2026/fancyhdr.sty 20 KB
- templates/iclr2026/iclr2026_conference.bib 629 B
- templates/iclr2026/iclr2026_conference.bst 26 KB
- templates/iclr2026/iclr2026_conference.pdf 196 KB
- templates/iclr2026/iclr2026_conference.sty 8.8 KB
- templates/iclr2026/iclr2026_conference.tex 17 KB
- templates/iclr2026/math_commands.tex 12 KB
- templates/iclr2026/natbib.sty 44 KB
- templates/icml2026/algorithm.sty 2.2 KB
- templates/icml2026/algorithmic.sty 7.2 KB
- templates/icml2026/example_paper.bib 2.0 KB
- templates/icml2026/example_paper.pdf 189 KB
- templates/icml2026/example_paper.tex 29 KB
- templates/icml2026/fancyhdr.sty 31 KB
- templates/icml2026/icml_numpapers.pdf 2.8 KB
- templates/icml2026/icml2026.bst 27 KB
- templates/icml2026/icml2026.sty 27 KB
- templates/neurips2025/extra_pkgs.tex 2.8 KB
- templates/neurips2025/main.tex 574 B
- templates/neurips2025/Makefile 1.0 KB
- templates/neurips2025/neurips.sty 11 KB
- templates/README.md 6.5 KB
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.
- 8d ago First seen · 1,628 lines · 22 tokens per session scan C ad6b059c628f
research-paper-writing is a skill published in the GitHub repository NousResearch/hermes-agent (244,603 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 16,698 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
maps-geography
Accurate maps from real geo data — use for any map, or whenever geography would make a good graphic for a deliverable.
rubyllm
Build and maintain Ruby or Rails applications with the RubyLLM AI framework. Use for chats, agents, tools, structured output, media generation, transcription, OCR, moderation, embeddings, reranking, Rails integration, and RubyLLM upgrades; not for contributing to the framework itself.
create-maps-and-spatial-plans
A guide for making maps and spatial plans based on real locations, boundaries, directions, scale, routes, floors, or access between places. It covers reference maps, navigation, thematic maps, service areas, site plans, and indoor wayfinding.
create-technical-diagrams
A guide for creating technical diagrams and engineering documents that show components, connections, processes, states, timing, interfaces, or cause and effect. It includes system and network diagrams, flow and sequence diagrams, electrical plans, mechanical sections, and scientific mechanism diagrams.
build-interactive-explainers
A guide for building interactive explainers, calculators, and simulations driven by an executable model. Users change inputs, steps, states, or events to understand a rule or see how a process develops over time.
biological-expert
Expert-level biology, biotechnology, genetics, bioinformatics, and computational biology. Use when the user mentions biology, biotechnology, genetics, bioinformatics, or genomics, or when the task involves Molecular Biology, Genomics & Bioinformatics, Systems Biology, or Data Analysis.