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 MilkyWay008/Hermes-OTG --skill complex-project-workflowgit clone --depth 1 https://github.com/MilkyWay008/Hermes-OTGWrote 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/milkyway008/hermes-otg/complex-project-workflow)<a href="https://agentmods.dev/skills/milkyway008/hermes-otg/complex-project-workflow"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/complex-project-workflow/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/milkyway008/hermes-otg/complex-project-workflow"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/complex-project-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Anti-Refusal · line 648 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00074 | $0.07860 |
| Opus 5 | $0.00037 | $0.03930 |
| Sonnet 5 | $0.00015 | $0.01572 |
| Haiku 4.5 | $0.00007 | $0.00786 |
Grade A, and why
complex-project-workflow 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 9d 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 — 691 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Complex Project Workflow
Overview
A universal, domain-agnostic project execution methodology. Works for anything — code builds, consulting engagements, content production, business process design, research projects, or any complex multi-phase delivery.
Core insight: Every project fails the same way — skip clarity, skip review, or try to do everything at once. This workflow hard-gates against all three.
Orchestrator discipline (HARD RULE): You stay at altitude. NEVER implement directly. NEVER review code/content directly. NEVER run tests/validation directly. Delegate everything to subagents or ACP agents. Your context window is for coordination, not implementation. Even duck council queries go through subagents.
When to Fire
This skill is the primary workflow for any project that has 2+ phases, 3+ components, or external stakeholders. If a task fits in a single conversation turn, don't load this — just do it directly.
Trigger examples:
- "Let's build a RustDesk fork that embeds MCP" → ✓ Load this
- "I need a consulting proposal for ABC Realty's AI agent setup" → ✓ Load this
- "Let's create a YouTube podcast series from scratch" → ✓ Load this
- "Can you fix this bug in my config file?" → ✗ Don't load this
WORKFLOW MODES
This skill supports two modes. Default is coding-centric. When the project involves clients, stakeholders, or non-technical deliverables, the skill auto-detects and switches to expanded mode.
Mode Detection
Check at session start:
- Is there a client or external stakeholder mentioned? → Use Expanded Mode
- Is the primary deliverable non-code (consulting doc, marketing plan, script, podcast, research paper)? → Use Expanded Mode
- Otherwise → Use Coding Mode (default)
In Expanded Mode, every phase gets the [CLIENT] treatment: draft for internal review first (duck council brief), then present to client for sign-off before advancing. The duck council acts as a "mock client" to sharpen deliverables before they reach real stakeholders.
What ships with it
1 file 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.
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.
- 9d ago First seen · 691 lines · 74 tokens per session scan A 1823fab7fb51
complex-project-workflow is a skill published in the GitHub repository MilkyWay008/Hermes-OTG (15 stars, last pushed 25d ago), licensed MIT. It adds 74 tokens to every session and 7,860 once invoked, about $0.0004 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 skills, from other repositories
acquiring-disk-image-with-dd-and-dcfldd
Create forensically sound bit-for-bit disk images with dd or dcfldd on a Linux forensic workstation, preserving evidence integrity through hash verification (MD5/SHA) during acquisition. Use when imaging a suspect drive, USB device, or memory card for investigation, preserving volatile disk evidence during incident…
analyzing-linux-kernel-rootkits
Detect kernel-level rootkits in Linux memory dumps using Volatility3 linux plugins (checksyscall, lsmod, hiddenmodules), rkhunter system scanning, and /proc vs /sys discrepancy analysis to identify hooked syscalls, hidden kernel modules, and tampered system structures.
hunt-auth-bypass
Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024)…
subdomain-enumeration
Map subdomains via crt.sh and subfinder at recon kickoff.
hunt-django
Hunt Django-specific vulnerabilities: DRF permission gaps, ORM injection, and admin exploitation.
tianya-gods-team
A decision-making system in which 20 fictional specialist viewpoints analyze one question in parallel before a coordinating AI combines them. It covers areas such as history, economics, relationships, technology, mysteries, and culture.