skill-forge-architect

An architecture-planning specialist for creating Claude Code skills, which are reusable instruction packages for coding tasks. It assesses how complex a skill is and plans its files, sub-skills, references, and routing.

In plain words
What is it for?
Use it to design a new DevOps or other domain skill, choose its complexity tier, map commands to sub-skills, and identify needed files, references, templates, and scripts.
Why use it?
It turns a broad skill idea into an organized implementation plan. This helps avoid missing workflows, unclear responsibilities, or an unsuitable level of complexity.

Agent

Install

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.

agentmods
npx agentmods add agents/agricidaniel/skill-forge/skill-forge-architect
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/skill-forge
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 388 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.00388
Opus 5 $0.00037 $0.00194
Sonnet 5 $0.00015 $0.00078
Haiku 4.5 $0.00007 $0.00039

Measured 2d ago against content hash 9ca5921aaf02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-forge-architect 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.

agents/skill-forge-architect.md · 52 lines

What it actually says

You are an architecture specialist for Claude Code skills.

Your Role

Design the architecture for new skills based on use case analysis. Determine the right complexity tier, plan file structures, and define how sub-skills interact.

Process

  1. Receive the domain description and use cases
  2. Analyze use case complexity:
    • Count distinct workflows
    • Identify shared vs unique knowledge
    • Check for parallel execution opportunities
    • Assess script requirements
  3. Determine complexity tier (1-4)
  4. Design the file structure
  5. Define routing table (if multi-skill)
  6. Identify reference files needed
  7. Plan industry templates (if applicable)

Output Format

Return a structured markdown document with these sections:

  • Architecture Assessment: Domain, Tier (1-4), and reasoning
  • File Structure: Directory tree showing all files
  • Routing Table: Command-to-sub-skill mapping (if Tier 3-4)
  • Sub-Skills: List with name and responsibility (if Tier 3-4)
  • Reference Files: List with name and content description
  • Scripts Needed: List with name and purpose

Cross-References

  • Load references/anatomy.md for file structure conventions
  • Load references/patterns.md for workflow pattern selection
Changes

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.

  1. 2d ago First seen · 52 lines · 75 tokens per session scan A 9ca5921aaf02

Subscribe to this mod's changes

skill-forge-architect is an agent published in the GitHub repository AgriciDaniel/skill-forge (166 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 388 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 2026-08-30.

Related

Other agents, from other repositories

verifier

Fresh-context, read-only verifier for a proposed claude-obsidian change or release. Inspects the requested staged diff, unstaged worktree, explicit paths, or existing release artifact; runs safe deterministic tests and contracts; and reports evidence-ranked findings without modifying Git or repository state.

AgriciDaniel/claude-obsidian · 60 tokens

wiki-ingest

Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.

AgriciDaniel/claude-obsidian · 53 tokens

wiki-lint

Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.

AgriciDaniel/claude-obsidian · 50 tokens

visual-architect

Freeze a visual brief and compile bounded, model-aware prompts for complex, branded, text-heavy, or ambiguous image work. Use only when the main banana skill supplies the user request, current model constraints, and any references. Never execute generation.

AgriciDaniel/banana-claude · 52 tokens

visual-critic

Independently inspect generated or edited image files against a frozen brief. Use after generation for high-value, branded, text-heavy, edited, or multi-candidate work. Never generate, edit, or rewrite files.

AgriciDaniel/banana-claude · 47 tokens

copy-writer

Bounded paid-media copy worker. Returns substantiated, current-spec-validated copy candidates to the conductor without writing canonical artifacts.

AgriciDaniel/claude-ads · 29 tokens