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/data-wise/craft/command-skill-token-efficiencynpx skills add Data-Wise/craft --skill command-skill-token-efficiencygit 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 | $0.00234 | $0.01827 |
| Opus 5 | $0.00117 | $0.00914 |
| Sonnet 5 | $0.00047 | $0.00365 |
| Haiku 4.5 | $0.00023 | $0.00183 |
Grade A, and why
command-skill-token-efficiency 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command/Skill Token Efficiency
Helps decide where content belongs when authoring or resizing a craft command, skill, or agent file, and runs the quantitative check that backs the decision up. Grew out of feature/token-usage-reduction (PR #232), which measured a 48% reduction in always-loaded line count across /refine (630→42 lines), /brainstorm (528→112 lines), and orchestrator-v2.md (1473→1212 lines). Line count and token count correlate but aren't identical — real /usage validation of the token-usage hypothesis is a separate, not-yet-completed step (see "Further reading" below). Full research and methodology: docs/specs/SPEC-token-efficiency-research-2026-06-30.md.
Why this matters
Command and agent files load into context in full, every time they're invoked — regardless of which part of the file is actually relevant that turn. Skills load conditionally, only when their description matches the conversation. That single structural fact is the entire lever this skill exists to apply: content that's genuinely procedure (the step-by-step logic of what a command does) costs less if it lives in a skill instead of the command file, because then it only loads when needed rather than every time.
This isn't a rule to apply mechanically everywhere — a short, focused command file is already fine. The skill matters most when a command file has grown large, or when a new command is being designed and there's a real choice about where its logic should live.
The classification: command vs. skill
When writing or reviewing a command/skill/agent file, sort its content into two buckets:
Stays in the command file (invocation-specific):
- Flag parsing and the documentation of those flags
- Frontmatter (
deprecated:,replaced-by:, argument hints) - Anything that has to be present even if skill-routing hasn't fired yet — the command always runs; the skill it might delegate to is conditional
Belongs in a skill (procedure):
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 · 81 lines · 234 tokens per session scan A b1d486aefecc
command-skill-token-efficiency is a skill published in the GitHub repository Data-Wise/craft (4 stars, last pushed 16d ago), licensed MIT. It adds 234 tokens to every session and 1,827 once invoked, about $0.0012 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 skills, from other repositories
github-actions-workflow
Scaffolds or audits a GitHub Actions CI/CD workflow for a project. Covers job structure, caching, secrets handling, concurrency groups, environment gates, and reusable workflows via workflowcall. Invoked when the user asks to set up CI, add a GitHub Actions workflow, improve pipeline performance, or share workflow…
specflow
Spec-driven development with executable contracts.
specflow-loop-selector
Selects the correct Specflow loop and forces a concrete run contract before work starts. Use when an agent is asked to start Specflow work, build a ticket, create/refine a PRD, investigate an existing product, run Gate D, choose between spec-build and feature-build, or "go find out about" Specflow loops. Compatible…
specflow-simulate
Simulates end-to-end usage of a Specflow story across multiple personas and divergent routes to discover gaps, edge cases, and unhandled branches BEFORE the story is built — then proposes each finding as a concrete story addition (new REQ, negative-path AC, Gherkin branch, or journey step). This is the high-value…
specflow-audit
Audits a Specflow story/ticket for spec-compliance and surgically uplifts it — adding only the missing executable contract sections (SQL/RLS, TypeScript interfaces, invariant codes, Gherkin, acceptance criteria, Definition of Done, data-testid coverage) — then runs a pre-flight gate that refuses to mark the ticket…
architecture-review
Conducts a comprehensive multi-perspective architecture review using ALL architecture team members. Use when the user requests "Start architecture review", "Full architecture review", "Review architecture for version X.Y.Z", "Conduct comprehensive review", or when they want assessment from multiple perspectives. Do…