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 commands/leoyang183/sync-agents-settings/sync-instructionsgit clone --depth 1 https://github.com/Leoyang183/sync-agents-settingsWhat 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 | $0.00041 | $0.00642 |
| Opus 5 | $0.00020 | $0.00321 |
| Sonnet 5 | $0.00008 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
sync-instructions 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 3d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync CLAUDE.md instruction files from Claude Code format to other AI agent formats.
Arguments
The user may pass target names: /sync-instructions gemini codex
If no targets specified, sync to all targets.
The user may also pass flags:
--no-backup— skip creating backup of target instruction files--import-mode inline|strip— how to handle standalone@importlines (inline= expand,strip= remove line)--report json— output machine-readable JSON summary (CI-friendly)
Execution Flow
-
Ask the user which scope to sync:
- Global (
~/.claude/CLAUDE.md) — syncs to agent-specific global instruction files - Local (
./.claude/CLAUDE.mdin current directory, fallback./CLAUDE.md) — syncs to project-level instruction files - Both (default) — syncs both global and local
- Global (
-
Parse targets from user arguments. Build the dry-run command:
npx sync-agents-settings sync-instructions --dry-run [--global|--local] --target <targets>Omit--global/--localif syncing both (this is the CLI default). Add--no-backupif the user specified it. -
Run the dry-run command. Present what will be written:
- Which instruction files will be created or updated
- Which targets will be skipped (e.g., Cursor global is unsupported — uses SQLite)
-
If any target files already exist, ask the user what to do:
- Overwrite — replace the existing file entirely
- Append — add Claude instructions after the existing content
- Skip — leave the existing file untouched
-
Run the actual command. IMPORTANT: Always pass
--on-conflict <action>to prevent the CLI from entering interactive mode (which does not work in Claude Code's bash execution):npx sync-agents-settings sync-instructions [--global|--local] --target <targets> --on-conflict <action>Add--no-backupif the user specified it. -
Present the final results: which files were synced, appended, or skipped.
- If
--report jsonis used, return raw JSON output and avoid text post-processing.
- If
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.
- 3d ago First seen · 51 lines · 41 tokens per session scan A df892488d9b5
sync-instructions is a command published in the GitHub repository Leoyang183/sync-agents-settings (8 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 642 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 commands, from other repositories
anti-pattern-czar
You are the Anti-Pattern Czar, an expert at identifying and fixing error handling anti-patterns.
om-incident-capture
Capture an incident from Slack channels, DMs, and threads into structured vault notes. Produces a complete incident work note with timeline, people, analysis, and brag doc entry.
om-dump
Freeform capture mode. Dump anything — conversations, decisions, incidents, wins, thoughts — and I'll route it all to the right notes with proper templates, frontmatter, and wikilinks.
maintainer
Meta-skill that loads all llmwiki governance docs and exposes the three maintainer slash commands.
release
Walk the llmwiki release process step by step.
wiki-synthesize
Synthesize wiki/sources/ .md pages from raw session transcripts using the configured LLM backend.