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 AkoliteZA/hermes-agent-idea-workflow --skill idea-to-implementation-docgit clone --depth 1 https://github.com/AkoliteZA/hermes-agent-idea-workflowWrote 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/akoliteza/hermes-agent-idea-workflow/idea-to-implementation-doc)<a href="https://agentmods.dev/skills/akoliteza/hermes-agent-idea-workflow/idea-to-implementation-doc"><img src="https://agentmods.dev/badge/skills/akoliteza/hermes-agent-idea-workflow/idea-to-implementation-doc/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/akoliteza/hermes-agent-idea-workflow/idea-to-implementation-doc"><img src="https://agentmods.dev/badge/skills/akoliteza/hermes-agent-idea-workflow/idea-to-implementation-doc.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.02548 |
| Opus 5 | $0.00015 | $0.01274 |
| Sonnet 5 | $0.00006 | $0.00510 |
| Haiku 4.5 | $0.00003 | $0.00255 |
Grade A, and why
idea-to-implementation-doc 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 10d 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea to Implementation Doc Workflow
Use this skill when the user wants to take one specific idea note and turn it into a technical implementation document.
This is not the top-level ideas index workflow. It works on a single idea file and produces a separate implementation plan.
Goal
Given a specific idea/design doc, create a detailed implementation document that:
- reviews the idea carefully
- researches similar products or existing apps
- identifies gaps or overlap with existing solutions
- proposes a concrete build approach
- outlines the system design, major components, and development phases
- converts the plan into an executable set of tasks and/or prompts for Hermes, Claude Code, Codex, OpenClaw, or another coding agent
- includes testing, verification, and acceptance criteria so “done” means the program works and is ready to use
- produces a single markdown file that can be handed to an agent as the build source of truth
Important constraints
- Focus on implementation strategy, not just product brainstorming.
- Research existing apps only to the extent needed to avoid reinventing something obvious.
- Do not over-engineer the stack. Choose the simplest viable approach.
- Keep the output practical and actionable.
- If the user asks for the doc to stay non-technical, stop at product-level architecture and planning.
- If the user wants code-level detail, include it in a separate section rather than mixing it into the product description.
Inputs
Primary input:
- one specific idea note, e.g.
ideas/my-app.md
Optional input:
- associated design doc, if it exists separately
- user constraints about stack, hosting, or platform
- deployment/data-location preference: local-only, self-hosted, Cloudflare, AWS, another cloud, or undecided
- platform targets: browser/web-only, Windows desktop, Mac desktop, cross-platform desktop, mobile web, iOS, Android, or explicitly no mobile
- accepted technical defaults or overrides for database, backend/runtime, frontend, auth, file/object storage, queues/jobs, realtime/sync, search, observability/logging, tests, and deployment/CI
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.
- 10d ago First seen · 341 lines · 29 tokens per session scan A 2b2b6eb35028
idea-to-implementation-doc is a skill published in the GitHub repository AkoliteZA/hermes-agent-idea-workflow (267 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 2,548 once invoked, about $0.0001 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
implement
Execute approved Hardproof tasks during IMPLEMENT with focused tests, durable task updates, and scope-controlled code changes.
orchestrate
Coordinate an active Hardproof run across discovery, design, planning, implementation, review, verification, delivery, and learning.
deliver
Prepare an inspectable Hardproof delivery during DELIVER with final scope, evidence, risks, rollback, and reproducible reporting.
design
Shape the smallest reversible Hardproof design from discovery evidence during DESIGN, including contracts, failures, and risks.
discover
Inspect a Hardproof run's request, repository, constraints, and unknowns during DISCOVERY before proposing a design.
learn
Close a Hardproof run during LEARN by capturing safe provenance-linked lessons or recording an explicit reason to skip them.