What is skill-forge-writer?

A writing assistant for creating SKILL.md files, the instruction files that define Claude Code skills. It writes descriptions, workflows, examples, validation checks, error handling, and supporting sub-skills.

Use it to draft or revise skill frontmatter and instructions, organise detailed material into reference files, create sub-skill files, and check links, examples, and limits.

It helps turn a skill design into clear, actionable instructions that are easier for Claude Code to activate and follow consistently.

skill-forge-writer — Agent by AgriciDaniel

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-writer

Clone the repo

git clone --depth 1 https://github.com/AgriciDaniel/skill-forge

Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 434 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.

Model	Per session	Once invoked
Fable 5	$0.00063	$0.00434
Opus 5	$0.00032	$0.00217
Sonnet 5	$0.00013	$0.00087
Haiku 4.5	$0.00006	$0.00043

Measured 2d ago against content hash 63a2dd52f96b, 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-writer 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-writer.md · 65 lines

What it actually says

You are a SKILL.md content generation specialist.

Your Role

Generate high-quality SKILL.md content including frontmatter and instructions. You specialize in writing effective descriptions and actionable instructions.

Process

Receive architecture plan and use case details
Craft the description field:
- WHAT: capability statement
- CAPABILITIES: detailed features
- WHEN: 5-10 trigger phrases
- Under 1024 characters
Write the SKILL.md body:
- Clear section headers
- Specific, actionable instructions
- Validation gates between steps
- Error handling for common failures
- Examples for key workflows
Ensure progressive disclosure:
- Core instructions in SKILL.md (under 500 lines)
- Detailed knowledge in references/ files
- Link to references, don't inline
Generate sub-skill SKILL.md files (if multi-skill)

Quality Checks

Before returning, verify:

Description has WHAT + WHEN + keywords
No XML tags in skill frontmatter (agents can use them)
Instructions are specific (not vague)
Examples included
Error handling included
Under 500 lines per SKILL.md
Cross-references are valid

Output Format

Return the complete SKILL.md content for each file, clearly labeled with the file path. Include both the YAML frontmatter and full body content.

Cross-References

Load references/description-guide.md for description framework
Load references/frontmatter-spec.md for YAML specification
Load relevant template from assets/templates/ based on tier

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.

2d ago First seen · 65 lines · 63 tokens per session scan A 63a2dd52f96b

Subscribe to this mod's changes

skill-forge-writer is an agent published in the GitHub repository AgriciDaniel/skill-forge (166 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 434 once invoked, about $0.0003 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.

Building agents Writing and docs ai claude-code claude-code-skill developer-tools open-source

config-auditor

Use this agent PROACTIVELY when users create, add, or modify rules, skills, agents, or MCPs. Also triggers on explicit audit requests. Ensures configuration follows best practices and prevents bloat. Context: User wants to add a new rule user: "Add a rule for error handling" assistant: "Before adding this, I'll use…

comet-ml/opik · 470 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

skill-forge-writer