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/w2ur/claude-code-setup/sync-setupgit clone --depth 1 https://github.com/w2ur/claude-code-setupWhat 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 | $0.00051 | $0.01587 |
| Opus 5 | $0.00026 | $0.00794 |
| Sonnet 5 | $0.00010 | $0.00317 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
sync-setup 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 yesterday.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync the claude-code-setup repo from the live ~/.claude/ configuration.
The rule that governs every step below
The arrow only points one way: ~/.claude/ → the repo. Everything under
commands/, agents/, skills/, hooks/ and claude-scripts/ is generated,
so fixing something by editing the repo's copy accomplishes nothing — the next
sync reverts it, and until 2026-08-23 it did so silently. sync.py now refuses
(exit 2) when a destination matches neither the incoming content nor HEAD,
which is what a hand edit looks like; --allow-dirty discards them on purpose.
The same applies to the SYNC-PRIVATE markers (the BEGIN / END pair), which
drop a private section from the published copy: they belong in the live
file, never in the repo. Every run reports how many regions it removed and
from where — if that count drops unexpectedly, a marker was lost in an edit to
the live source. Note this file deliberately never spells the pair out
contiguously: it is a sync SOURCE, so a literal marker here would be read as a
real one. scripts/README.md in the repo is owner-maintained, never synced, and
carries the full syntax.
Owner-maintained files are the exception and are never synced: README.md,
docs/, hooks/README.md, claude-scripts/README.md, root-level files.
Step 1: Run sync.py
cd ~/Dev/claude-code-setup && ./scripts/sync.py $0
If $0 is --dry-run or --audit-only, stop after this step.
If it exits 2 refusing to overwrite hand edits, do not reach for
--allow-dirty first. Read the named files: the change they carry is usually
one that belongs in ~/.claude/, and porting it there is the fix.
Step 2: Verify stale-file cleanup
sync.py now prunes orphans automatically: any file under a synced root
(commands/, agents/, skills/, hooks/, claude-scripts/) whose live
source has disappeared is deleted on a real run (reported on --dry-run) and listed under
the ── Orphans ── section of the output. Common cases: renamed agents (e.g.,
old architect.md after rename to troubleshooter.md), deleted commands,
removed skills, retired hooks.
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.
- yesterday First seen · 119 lines · 51 tokens per session scan A 2e333f18fb70
sync-setup is a command published in the GitHub repository w2ur/claude-code-setup (2 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 1,587 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 2026-08-31.
Other commands, from other repositories
vibe-agents
Step 4 of the vibe-coding workflow: generate AGENTS.md + tool configs so the AI builder stays on track.
icon-lookup
Search for icons by name, or identify a PUA character.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
roadmap
Generate or update a per-release roadmap from the PRD and analysis documents. Triages features, groups into phases, and produces a structured roadmap.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
adr
Architecture Decision Record (ADR) command. Documents architectural decisions in a structured format.