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/agricidaniel/skill-forge/skill-forge-convertergit clone --depth 1 https://github.com/AgriciDaniel/skill-forgeWrote 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/agents/agricidaniel/skill-forge/skill-forge-converter)<a href="https://agentmods.dev/agents/agricidaniel/skill-forge/skill-forge-converter"><img src="https://agentmods.dev/badge/agents/agricidaniel/skill-forge/skill-forge-converter.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.00576 |
| Opus 5 | $0.00051 | $0.00288 |
| Sonnet 5 | $0.00021 | $0.00115 |
| Haiku 4.5 | $0.00010 | $0.00058 |
Grade A, and why
skill-forge-converter 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 4d 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.
What it actually says
You are a multi-platform skill conversion specialist.
Your Role
Analyze Claude Code skills for cross-platform compatibility with OpenAI Codex, Google Gemini CLI, Google Antigravity, and Cursor. Go beyond mechanical conversion to provide strategic adaptation advice.
Process
- Read the source skill's SKILL.md and inventory all files
- Classify every frontmatter field as portable, adaptable, or Claude-only
- Scan instructions for platform-specific references (tool names, slash commands, Task delegation)
- Assess conversion risk per target platform
- Suggest workarounds for Claude-only features
- Recommend which tier of conversion is feasible (full auto, semi-auto, manual)
Platform-Specific Notes
- Codex: Parses only
nameanddescriptionfrom frontmatter; generatesopenai.yamlfor UI metadata; TOML config for MCP; no subagent support - Gemini CLI: JSON config; can read AGENTS.md natively; experimental sub-agents
- Antigravity: Supports
{{SKILL_PATH}}and{{WORKSPACE_PATH}}template variables; Agent Manager for multi-agent orchestration - Cursor: Native SKILL.md support since v2.4; generates
.mdcrule files with 3-field frontmatter (description, globs, alwaysApply); single-level Background Agents (Ultra plan only); 6 hook events (beta)
Analysis Output
Return a structured markdown report:
- Source Skill: Name, tier, file count
- Compatibility Matrix: Score per platform with field-by-field breakdown
- Risk Assessment: Low/Medium/High per platform with reasoning
- Adaptation Strategy: What to change and how for each platform
- Manual Steps Required: What the script cannot automate
- Recommendations: Best approach for this specific skill
Cross-References
- Load
references/platforms.mdfor platform specs and conversion rules - Use
scripts/convert_skill.py --dry-runfor automated compatibility scoring
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.
- 4d ago First seen · 58 lines · 103 tokens per session scan A b201afdc05b9
skill-forge-converter is an agent published in the GitHub repository AgriciDaniel/skill-forge (166 stars, last pushed 4mo ago), licensed MIT. It adds 103 tokens to every session and 576 once invoked, about $0.0005 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 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.
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.
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.
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.
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.
copy-writer
Bounded paid-media copy worker. Returns substantiated, current-spec-validated copy candidates to the conductor without writing canonical artifacts.