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/data-wise/craft/smart-helpgit clone --depth 1 https://github.com/Data-Wise/craftWhat 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 | $0.00007 | $0.02222 |
| Opus 5 | $0.00003 | $0.01111 |
| Sonnet 5 | $0.00001 | $0.00444 |
| Haiku 4.5 | $0.00001 | $0.00222 |
Grade A, and why
smart-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 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/craft:smart-help - Context-Aware Help
Get intelligent help based on your project and question.
Usage
/craft:smart-help # Show relevant commands for current project
/craft:smart-help <topic> # Get help on specific topic
/craft:smart-help "how do I..." # Answer questions about workflows
--refine (prompt pre-processing)
When --refine is set, do NOT act on the raw topic argument. First invoke the
prompt-refiner skill with the argument and project context. Follow that
skill's canonical flow (before/after box → fenced refined-prompt block →
4-way confirm: Execute now / Copy for elsewhere / Edit first / Skip; --yes
or auto mode auto-accepts Execute now). If the user picks "Copy for
elsewhere," stop here — do not start help lookup. Otherwise proceed using
the prompt the skill returns. Off by default (--refine is opt-in): most
topic arguments here are a single keyword or a short question, where the
rewrite round-trip adds little over the skip-gate already handling terse
prompts.
Context-Aware Suggestions
Based on Project Type
Python Project:
╭─ Suggested Commands for Python Project ─────────────╮
│ │
│ Development: │
│ /craft:code:lint ruff, flake8 checks │
│ /craft:test pytest runner │
│ /craft:test --coverage coverage report │
│ │
│ Quality: │
│ /craft:code:deps-audit pip-audit security │
│ /craft:ci:local pre-commit simulation │
│ │
│ Release: │
│ /craft:code:release PyPI workflow │
│ /craft:docs:changelog update CHANGELOG.md │
│ │
╰─────────────────────────────────────────────────────╯
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 · 289 lines · 7 tokens per session scan A fbf288baa73f
smart-help is a command published in the GitHub repository Data-Wise/craft (4 stars, last pushed 15d ago), licensed MIT. It adds 7 tokens to every session and 2,222 once invoked, about $0.0000 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
readme-audit
Audit a README's reading flow by treating it as a conversion funnel. Every section is evaluated against a target reader and a terminal action. Produces a structured audit blueprint that feeds directly into /readme-restructure.
readme-restructure
Execute a /readme-audit blueprint. Rewrites the README to the evaluator → conversion → links structure and creates linked docs by extracting and reorganising existing content.
build-fix
Fix build and type failures with minimal diffs.
checkpoint
Record a verified checkpoint before the next phase.
doctor
Check the install surface for missing files and invalid manifests.
feature-dev
Drive a feature from plan to implementation to review.