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-helpnpx skills add ATTCKDigital/smith --skill smith-helpgit 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 | $0.00025 | $0.06349 |
| Opus 5 | $0.00013 | $0.03174 |
| Sonnet 5 | $0.00005 | $0.01270 |
| Haiku 4.5 | $0.00003 | $0.00635 |
Grade A, and why
smith-help 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 — 773 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smith Help System
Display help for Smith commands. With no arguments, shows the full command overview. With a command name, shows detailed help including syntax, flags, examples, and workflow context.
Arguments: $ARGUMENTS
Behavior
This action is read-only — it does not modify any files. It should always be handled directly by the current session, never delegated to a sub-agent.
No Arguments — Full Overview
When invoked with no arguments, display this overview:
SMITH — Forge Your Workflow
FEATURE DEVELOPMENT
/smith-new Start a new feature end-to-end
/smith-specify Create or update a feature spec
/smith-clarify Ask clarification questions on a spec
/smith-plan Generate implementation plan from spec
/smith-tasks Break plan into ordered tasks
/smith-analyze Check consistency across spec/plan/tasks
/smith-implement Execute all tasks sequentially
/smith-build Autonomous build (tasks → implement → test → PR → merge)
/smith-checklist Generate quality checklist for spec/plan
/smith-bugfix Autonomous bugfix (branch → fix → test → PR → merge)
/smith-debug Diagnostic investigation (gather evidence → report → optional bugfix)
VAULT
/smith-vault Dashboard — recent sessions, agents, queue status
/smith-vault sessions List session logs
/smith-vault agents List sub-agent types and history
/smith-vault queue Show pending queue items
/smith-vault projects List all registered projects
/smith-vault status Vault health and routing metrics
QUEUE
/smith-queue add Add a task to the queue
/smith-queue list Show pending tasks by priority
/smith-queue process Pick and process a task (interactive, --next, --all, or <file>)
/smith-queue batch Alias for process --all
/smith-queue status Show tasks grouped by status
/smith-queue schedule Schedule a task for a specific time
/smith-queue history View completed and failed tasks
/smith-queue edit Modify a queued task
/smith-queue promote Change task from autonomous to interactive
/smith-queue demote Change task from interactive to autonomous
/smith-queue requeue Reset a failed task to pending
/smith-queue scheduler Manage the automated 2am batch scheduler
BANK
/smith-bank Deposit an idea from the current conversation
/smith-bank list Show all banked ideas (--priority, --system filters)
/smith-bank process <id> Withdraw idea and start /smith-new workflow
/smith-bank edit <id> Edit a banked idea's details
/smith-bank remove <id> Archive a banked idea
/smith-bank prioritize <id> --priority <level> Change priority
LEARNING
/smith-reflect Analyze completed workflow and extract lessons to the Ledger
/smith-reflect --last N Analyze last N workflows in batch
/smith-reflect --failure Learn from recent failures specifically
/smith-ledger Browse the Ledger dashboard
/smith-ledger list List all learned patterns by category
/smith-ledger search Search across all Ledger entries
/smith-ledger prune Remove stale low-confidence entries
/smith-ledger reset Archive and restart the Ledger
/smith-ledger reconcile Trigger Ledger self-maintenance (merge, prune, budget enforce)
/smith-ledger reconcile --dry-run Preview reconciliation without modifying files
/smith-ledger reconcile --force Bypass lock and threshold checks
/smith-ledger reconcile --status Check if reconciliation is needed
REPORTS
/smith-report Generate client-facing project report
PROJECT
/smith Bootstrap a new project with Smith workflow
/smith-constitution Create or update project constitution
/smith-taskstoissues Convert tasks.md to GitHub Issues
/smith-migrate-specs Migrate flat specs into system-based hierarchy
/smith-migrate-system-paths Add `paths:` frontmatter to existing system specs
SESSION
/smith-finish Commit, push, merge, update specs, clean workspace
/smith-sync Sweep & push team-shareable .smith/ artifacts to the default branch
HELP
/smith-help This overview
/smith-help <command> Detailed help for a specific command
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 · 773 lines · 25 tokens per session scan A d9c6b12d694f
smith-help is a skill published in the GitHub repository ATTCKDigital/smith (52 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 6,349 once invoked, about $0.0001 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…