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/deltadbu/wit-skill/witnpx skills add deltadbu/WIT-skill --skill witgit clone --depth 1 https://github.com/deltadbu/WIT-skillWhat 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 | $0.00093 | $0.02485 |
| Opus 5 | $0.00046 | $0.01242 |
| Sonnet 5 | $0.00019 | $0.00497 |
| Haiku 4.5 | $0.00009 | $0.00248 |
Grade A, and why
wit 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- case-studies/Applying-WIT-to-MSFold-cn.md 33 KB
- case-studies/Applying-WIT-to-MSFold.md 34 KB
- case-studies/README.md 85 B
- README.md 132 B
- references/WIT-Scientific-thinking-and-writing-skill.md 68 KB
- references/WIT-科学思考及写作skill.md 66 KB
- tests/Assess-WIT-using-AlphaGo-cn.md 15 KB
- tests/Assess-WIT-using-AlphaGo.md 17 KB
- tests/README.md 81 B
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 · 105 lines · 93 tokens per session scan A 45dc6b2a118c
wit is a skill published in the GitHub repository deltadbu/WIT-skill (22 stars, last pushed 4d ago), with no licence file. It adds 93 tokens to every session and 2,485 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
commit
Atomic git commit with conventional message. Use when the user says "commit", "save my changes", "commit this", or wants to create a git commit. Stages specific files, writes a conventional commit message with body explaining non-obvious decisions. Never uses git add -A.
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
project-scaffolder
Use when a learning plan requires runnable chapter files, a multi-lesson coding course, a project-based route, or a workspace the learner will open in an editor.
lovable-codebase-audit-cleanup
Perform a two-phase codebase rationalization on a Lovable project — a comprehensive read-only audit to find dead code, unused code, obsolete dependencies, duplicated implementations, and maintainability risks, followed by a strictly-scoped, approval-gated cleanup of only the batches the user explicitly approves. Use…
art-direction
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers landing pages, marketing sites, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty…
responsive
Use when the user wants an app, site, page, or component to work correctly on every screen size — "make it responsive", "fix it on mobile", "it breaks on my phone", "it doesn't look right on tablet", "there's horizontal scrolling", "the layout overflows", "make it work on small screens", "test it at different…