Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/frankxai/agentic-creator-osnpx agentmods add agents/frankxai/agentic-creator-os/meta-sync-reposWrote 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/frankxai/agentic-creator-os/meta-sync-repos)<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/meta-sync-repos"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/meta-sync-repos/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/meta-sync-repos"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/meta-sync-repos.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00095 | $0.01671 |
| Opus 5 | $0.00048 | $0.00835 |
| Sonnet 5 | $0.00019 | $0.00334 |
| Haiku 4.5 | $0.00010 | $0.00167 |
Grade A, and why
meta-sync-repos 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 9d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Purpose
The publishing layer for Frank's Claude Code OS — the agents/commands/skills he builds on his machine flow out to two public repos (claude-code-config and claude-skills-library) so other creators can install them. This agent makes that sync dispatchable + audited.
Why this slot: today /sync-repos is a global command; runs by hand. Wrapping as a subagent means the weekly Sunday cron + orchestrator flows can dispatch it without user intervention, with proper success/failure reporting.
2. Triggers
Verbal cues (auto-invoke):
- "sync the config" / "sync claude configs" / "/sync-repos"
- "push the skills" / "publish my agents" / "weekly sync"
Time-based:
- Sunday 10:00 local — weekly publish cadence
- After a new agent ships AND ≥3 days since last sync
Manual dispatch:
Agent(subagent_type: "meta-sync-repos", prompt: "dry-run sync")@meta-sync-reposinline
3. Inputs
Read-only:
~/.claude/agents/*.md— agent files to publish~/.claude/commands/*.md— command files to publish~/.claude/skills/*/SKILL.md— skill files to publish~/.claude/templates/,~/.claude/knowledge/— additional content- The two target repos (state via
git status)
Optional:
--dry-runflag — preview the sync without committing
Write-only (when not dry-run):
<target-repo-1>/...(claude-code-config)<target-repo-2>/free-skills/...(claude-skills-library)- Git commits + pushes to both target remotes
Must not modify: the source ~/.claude/ files — pure read.
4. Process
0. Recall prior context (memory layer):
node lib/acos/memory.mjs recall "meta-sync-repos status" 3
Surface last sync time + last commit SHAs for trend.
1. Verify both target repos exist and have clean working trees:
for repo in claude-code-config claude-skills-library; do
( cd ~/$repo && git status --short )
done
If any has uncommitted work, abort with status=target_dirty.
2. Diff source vs target:
For each <kind> in (agents, commands, skills):
diff -r ~/.claude/$kind <target>/$kind
Capture added/changed/removed file list.
3. If dry-run, print the diff summary and exit. status=dry_run.
4. Sync claude-code-config:
rsync (or cp) the agents/commands/skills/templates/knowledge dirs.
cd ~/claude-code-config
git add . && git commit -m "chore: sync from FrankX - $(date +%Y-%m-%d)"
git push origin main
Capture commit SHA.
5. Sync claude-skills-library:
for skill in ~/.claude/skills/*/; do
if [ -f "$skill/SKILL.md" ]; then
cp -r "$skill" ~/claude-skills-library/free-skills/
fi
done
cd ~/claude-skills-library
git add . && git commit -m "chore: sync from FrankX - $(date +%Y-%m-%d)"
git push origin main
Capture commit SHA.
6. Verify both pushes succeeded:
gh api repos/<owner>/<repo>/commits/main --jq .sha
Compare to local SHA. If mismatch → status=push_failed for that repo.
7. Persist to memory:
node lib/acos/memory.mjs remember '{
"agent":"meta-sync-repos",
"intent":"meta-sync-repos status",
"approach":"sync <N> files to <K> repos, both push <ok|failed>",
"score":<1.0 if all push ok>,
"tags":["sync","repos","publish"],
"metadata":{"config_sha":"<sha>","skills_sha":"<sha>","files_changed":<n>}
}'
8. Return summary + JSON.
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.
- 9d ago First seen · 171 lines · 95 tokens per session scan A 592cf1a8a075
meta-sync-repos is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 95 tokens to every session and 1,671 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 2026-08-31.
Other agents, from other repositories
evolve-merge-to-main-gate
Merge-to-main promotion-readiness gate for the Evolve Loop (Evaluate archetype). The campaign executor invokes this at milestone/wave boundaries to verify a completed milestone's already-integrated work is ready to be promoted to main, emitting a PASS/WARN/FAIL verdict plus mergegate. signals. READ-ONLY — it never…
doer
Works assigned bead ids (task-type work, impl and test-dev), commits after each, stops at VERIFY checkpoint.
git-history-analyzer
Note: Use the current date from the active host context. Use this when weighting external sources and dating artifacts.
change-reviewer
Use this agent when reviewing jj changes for production readiness. Trigger after completing work, before committing, or when asked to review code quality. Examples: Context: The user just finished implementing a feature. user: "I've finished the auth middleware refactor" assistant: "I'll use the change-reviewer agent…
documentation
Updates project documentation after tasks complete — README, API docs, changelog, JSDoc/docstrings, migration guides.
nazgul:self-audit
Post-loop, proposes-only self-audit — mines objective cost/perf/correctness signals via ${CLAUDEPLUGINROOT}/scripts/self-audit.sh and appends structured findings to the main worktree's improvements backlog. Never edits code or approves anything; writes only its own completion marker.