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 instructions/oghie/skillsets/agents-mdgit clone --depth 1 https://github.com/oghie/skillsetsWrote 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/instructions/oghie/skillsets/agents-md)<a href="https://agentmods.dev/instructions/oghie/skillsets/agents-md"><img src="https://agentmods.dev/badge/instructions/oghie/skillsets/agents-md.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 | $0.00694 | $0.00694 |
| Opus 5 | $0.00347 | $0.00347 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
skillsets AGENTS.md 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 4d 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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skillsets
This repository is a single plugin that bundles nine self-contained engineering and research skills compatible with Hermes, Claude Code, Codex, OpenCode, and Antigravity (Gemini). Each skill is a model-agnostic instruction set: it classifies the task, gathers evidence, applies domain references, and verifies before handoff.
Each skill auto-surfaces by its name and description. When a task matches a skill's description, read that skill's skills/<name>/SKILL.md first and follow its workflow. The detailed tasks/, references/, and scripts/ under each skill directory are the source of truth.
Hermes reads HERMES.md for project context and discovers skills through the plugin manifest at .hermes-plugin/plugin.json. OpenCode reads AGENTS.md and discovers skills through .opencode/skills/, which points back to skills/. Do not duplicate skill source material across platform-specific mirrors.
Skills
skills/android-offsec— Android offensive security, forensic extraction, mobile app exploitation: lock screen bypass, APK reversing, deeplink fuzzing, kernel/GPU exploit research, rogue WiFi attacks, deepfake social engineering, and chain-of-custody device investigation.skills/cyber-security-operations— Cyber security operations: detection engineering and threat hunting, DFIR/forensics, incident response/SOC, vulnerability management, supply chain/DevSecOps, crypto/AI emerging threats, and offensive security tradecraft.skills/academic-research-journal— Evaluate, design, draft, revise, and stress-test academic articles, literature and systematic reviews, journal submissions, reviewer responses, and source/integrity audits.skills/data-architect-engineering— Design, review, migrate, optimize, secure, and operate SQL, NoSQL, vector, graph, document, time-series, search, cache, big-data, lakehouse, and warehouse systems, including DBMS internals.skills/device-driver-development— Develop, review, debug, port, and engineer Linux kernel device drivers, kernel modules, device tree bindings, bus clients, DMA/IRQ/memory paths, userspace ABIs, and hardware bring-up.skills/realtime-systems-coding— Build concurrent, parallel, distributed, real-time, and network-dataplane software: locks, monitors, MPI/CSP, DPDK/VPP, eBPF/XDP/AF_XDP, SR-IOV, RDMA, and RMS/EDF scheduling.skills/software-architecture-engineering-uap— Design, evaluate, document, modernize, refactor, and implement software architecture and code structure: requirements, context, style selection, architecture views, clean code, NFR tactics, IAM/auth, security patterns, cost, fitness functions, and ADR/RFC work.skills/tech-leadership— Advise, plan, review, and operate CTO and technology leadership work across strategy, cybersecurity, requirements, framework selection, people, delivery, risk, KPIs, roadmap, budgeting, governance, and stakeholder communication.skills/uiux-frontend-engineering— Design, review, implement, and validate UI/UX and frontend experiences for web, mobile, responsive apps, design systems, accessibility, theme/token application, and XR/spatial interfaces.
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.
- 4d ago First seen · 20 lines · 694 tokens per session scan A e5770bf6c5e4
skillsets AGENTS.md is an instructions file published in the GitHub repository oghie/skillsets (9 stars, last pushed 1mo ago), licensed MIT. It adds 694 tokens to every session, about $0.0035 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 2026-08-31.
Other instructions, from other repositories
med-paper-assistant AGENTS.md
AGENTS.md instructions for u9401066/med-paper-assistant, covering agents.md - vs code copilot agent 指引, 核心價值：逐步多輪演進, 運行模式, 檔案保護（normal/research） and 專案規則.
scientific-writing CLAUDE.md
Instructions for koljaschoepe/scientific-writing, covering scientific writing framework, schnellstart, workflow, befehle and regeln für generierte texte.
sourceright AGENTS.md
AGENTS.md instructions for edithatogo/sourceright, covering sourceright codex instructions, codev - ai agent instructions, project overview, available protocols and file resolution (how codev finds protocols and templates).
scitex-python CLAUDE.md
Claude Code instructions for scitex-ai/scitex-python, covering workflow orchestration, 1. plan mode default, 2. subagent strategy, 3. self-improvement loop and 4. verification before done.
avoid-overkill AGENTS.md
AGENTS.md instructions for 6Kmfi6HP/avoid-overkill: This repository packages a reusable Agent Skill and plugin manifests.
academic-writer-skills AGENTS.md
AGENTS.md instructions for muhammad1438/academic-writer-skills, covering academic writer skills — multi-agent workflow guide, skill dependency map, pipeline patterns, pattern 1: full research paper and pattern 2: grant application pipeline.