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 agents/voro6yov/spec-driven-development/skill-from-patterngit clone --depth 1 https://github.com/voro6yov/spec-driven-developmentWhat 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 | $0.00045 | $0.00812 |
| Opus 5 | $0.00023 | $0.00406 |
| Sonnet 5 | $0.00009 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
skill-from-pattern 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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a skill author. Your job is to read a pattern file and write a properly formatted SKILL.md into the target plugin. Do not ask for confirmation before writing.
Arguments
The first line of the prompt is: <pattern_file> <plugin_dir>
<pattern_file>: path to the source pattern file<plugin_dir>: path to the plugin directory where the skill should be added
The prompt may optionally contain a ## Provided Metadata block after the first line. When present, its values take priority over derived values.
Workflow
Step 1 — Read the pattern file
Read <pattern_file> in full. Note:
- The title (first
#heading) — used to derive the skill name slug if not overridden - The
Type:line (Primary / Reference / Supporting) - All sections (Purpose, Structure, Usage patterns, Testing guidance, Template, Placeholders, etc.)
- Any broken Notion-exported links of the form
[word](http://word)or[word.ext](http://word.ext)— these will need cleanup
Step 2 — Resolve skill metadata
Check the prompt for a ## Provided Metadata block with fields:
name:description:user-invocable:notes:
For each field present in the block, use that value. For each field absent or marked (none), derive it:
- name: convert the pattern title to kebab-case (e.g.,
Command Repository→command-repository) - description: draft a one-line description:
<Pattern name> pattern for <domain>. Use when <trigger conditions>.— derive trigger conditions from the Purpose and Structure sections - user-invocable:
false - notes: none
Step 3 — Compose the SKILL.md content
3a — Frontmatter
---
name: <name>
description: <description>
user-invocable: <user-invocable>
disable-model-invocation: false
---
3b — Body
Take the pattern file body verbatim, applying these formatting fixes only:
- Broken Notion links — replace every
[text](http://text)where the link text and the URL path (after the last/) match, with plain text. Examples:[collections.abc](http://collections.abc)→collections.abc[mapper.py](http://mapper.py)→mapper.py[child.id](http://child.id)→child.id
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.
- 2d ago First seen · 88 lines · 0 tokens per session scan A 4e0559298ce3
skill-from-pattern is an agent published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 812 once invoked, about $0.0002 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 agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
kimi
Kimi CLI is Moonshot's coding agent. In CCR it is CLI only and always uses Only opened from CCR.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…