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 skills add atman-33/workhub --skill laddergit clone --depth 1 https://github.com/atman-33/workhubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/atman-33/workhub/ladder)<a href="https://agentmods.dev/skills/atman-33/workhub/ladder"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/ladder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/atman-33/workhub/ladder"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/ladder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00133 | $0.00694 |
| Opus 5.5 | $0.00053 | $0.00278 |
| Sonnet 5.5 | $0.00027 | $0.00139 |
| Haiku 4.5 | $0.00013 | $0.00069 |
Grade A, and why
ladder 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 26d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ladder
You run the ladder; the user climbs it. Each rung is one Level, and the user's own words fill it. Your job is the next question, the paraphrase that closes a Level, and the ledger of what is settled.
Pick the direction
- down — starts from an abstract concept and ends at conditions someone could observe. Level definitions: references/down.md.
- up — starts from a symptom and ends at the state worth aiming for. Level definitions: references/up.md.
Take the direction from the argument, or from the opener: a concept to pin
down is down, something going wrong is up. When the opener fits both, ask
which. Read the matching reference before the first question.
Each turn
Open with the position on one line — Level 3/7 — Purpose — then ask exactly
one question about the current Level. Build the question from what the user
has said so far, in their terms.
When an abstract word surfaces mid-answer ("alignment", "quality"), ask what it means here before building on it. Its definition goes in the ledger.
Closing a Level
A Level closes on agreement, and nothing else:
- Restate the Level's content in one sentence, in the user's words.
- Ask: "Is that right, or what would you change?"
- On an explicit yes, record it in the ledger and move to the next Level. On a change, fold it in and ask again.
The next Level always starts from agreed content. Unagreed material waits in the ledger's Open list, where the user can see it.
The ledger
Show it when a Level closes and whenever the user asks — not every turn.
**Agreed**
- L1 Concept: …
- L2 Definition: …
**Open**
- …
**Next**
- …
Strawman on request
When the user asks you to just answer ("案を出して", "what would you say?"),
offer one hypothesis for the current Level only, labelled Strawman:.
It closes the same way — paraphrase, then agreement — before anything builds
on it.
Finishing
The ladder is done when the last Level of the direction is agreed. Output the structure with the direction's template from its reference file, filled only with agreed content, with Open items listed at the end. Keep it in chat; write a file only when asked, to the path the user names.
What ships with it
2 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.
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.
- 26d ago First seen · 72 lines · 133 tokens per session scan A 0f331109c363
ladder is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed yesterday), licensed MIT. It adds 133 tokens to every session and 694 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-20.
Other skills, from other repositories
academic-paper-workflow
Use when a user needs to plan, compose, or revise an academic paper in a staged workflow.
aetox-teach
สอนคนใช้ Aetox — ทำอะไรได้บ้างในคำที่คนเข้าใจ ห้องไหนไว้ทำอะไร ห้าอย่างที่คนใหม่ต้องรู้ และวิธีสอนด้วยการลงมือทำงานจริงของเขาแทนการบรรยาย · อ่านเมื่อผู้ใช้ถามว่าแอปนี้ทำอะไรได้ ถามวิธีใช้ หรือเพิ่งเปิดครั้งแรก.
interview-prep-generator
Generate STAR stories, practice questions, and talking points from resume.
async-learning-teacher
Transform saved links, papers, articles, posts, videos, and reference collections into approachable AI teaching artifacts for later study. Use when a user wants to queue learning material, create a readable explanation from a source, teach a paper or post step by step, or run an interactive tutor that validates…
digest
Generate a structured vibe-learn learning digest of the current coding session from .vibe-learn/session-log.jsonl.
readmd-style-custom
Generate custom CSS rules and HTML head tags for ReadMD document styling.