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 skills/attckdigital/smith/smith-syncnpx skills add ATTCKDigital/smith --skill smith-syncgit clone --depth 1 https://github.com/ATTCKDigital/smithWhat 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 | $0.00092 | $0.02058 |
| Opus 5 | $0.00046 | $0.01029 |
| Sonnet 5 | $0.00018 | $0.00412 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade A, and why
smith-sync 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smith — Sync Vault, Index & Debug-Report Artifacts
Skill Purpose
Smith workflows stage only the files they explicitly touch (every workflow
enforces "never git add -A"). So the team-shareable .smith/ artifacts made
committable by the gitignore policy — index/manifest.md, the
index/files/ + index/systems/ .meta describe layer, vault/ledger/,
vault/bank/, vault/agents/, vault/sessions/*.md — accumulate unstaged in
the primary repo and never reach teammates. The same is true of the debug
reports /smith-debug writes to .specify/systems/<system>/debug/ (or
.specify/debug/ in un-systematized projects): the debug workflow is read-only
and never commits, so its reports would otherwise sit untracked forever.
/smith-sync closes that loop: it sweeps the committable .smith/ artifacts
and any debug reports into one chore commit and pushes it directly to the
default branch, giving the repo owner full, reliable transparency into activity
without anyone needing to remember a manual command.
This skill operates in the primary repo on the default branch — NOT a
worktree. The artifacts live in the primary repo's .smith/ (vault logging,
index rebuilds, reflection writes), outside the /tmp worktree a workflow's PR
is built from. That is why the sync runs as a terminal step after worktree
cleanup, and why it cannot be part of a worktree's PR.
When This Runs
- Automatically as the final step of
/smith-new,/smith-bugfix, and/smith-debug(chained in those skills). - Manually anytime via
/smith-sync. It is idempotent and safe to re-run.
How It Works
git add .smith/ relies on .gitignore as the filter: git natively skips the
ignored paths (.current-session*, queue/, todo/, active-workflows/,
timesheets/, checkpoints, config/) and stages only the committable ones.
There is no sentinel-block parsing — the gitignore policy is the single
source of truth, so when the policy changes (via /smith-update) the sweep
automatically follows.
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 · 179 lines · 92 tokens per session scan A d6852905f087
smith-sync is a skill published in the GitHub repository ATTCKDigital/smith (52 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 2,058 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…