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/iamk77/skill/typenpx skills add IamK77/Skill --skill typegit clone --depth 1 https://github.com/IamK77/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 | $0.00234 | $0.04502 |
| Opus 5 | $0.00117 | $0.02251 |
| Sonnet 5 | $0.00047 | $0.00900 |
| Haiku 4.5 | $0.00023 | $0.00450 |
Grade A, and why
type 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
type
!checklist init ${CLAUDE_SKILL_DIR} --force
An atelier is a craftsman's workshop where every detail is deliberate and traceable — nothing slapped on, nothing "good enough for now." type is the atelier suite's text lens: where the scale is set, the rhythm committed, the optical details sharpened, and the system stress-tested against every language it will ever carry. Its product is a written type system: a modular scale expressed as tokens, a spacing scale on the same rem rhythm, and an internationalized-text posture that survives BiDi, CJK, IME composition, and the full Intl API — each committed before components consume it. It runs across three gated stages and will not advance past a GATE until the checklist tool clears it — order enforced, substance yours.
The governing fact: a polished typographic surface is values derived from a small system; an amateur one is values picked one at a time. The same font-size: 14px typed in thirty places, a heading scaled by nudging until it "looks right", a padding: 13px here and margin-top: 22px there — each is a hand-picked value, and their sum is the visual incoherence the eye reads as "cheap" without being able to name it. The subtler failure is text that looks fine in English and falls apart in German (30% longer strings), Arabic (right-to-left layout breaks), Japanese (no CLS-free fallback, wrong line-breaking), or Polish (pluralization assumes only two forms). Both failures share the same root: a value or behavior that was never part of a system, just assumed to work.
This is where the agent era bites:
- The agent nudges sizes by eye. It will emit
font-size: 14pxhere,font-size: 17pxthere,font-size: 13pxon that label — each "looks right" in isolation, the set reads as a draft. It has no sense of ratio or rhythm. The sizes must come from one decided scale, not per-call taste. - The agent picks magic spacing.
padding: 13px,margin-top: 22px, a different gutter per component — the most pervasive single tell in real UIs. A spacing value not in the scale does not ship. - The agent tests only in English. It never sets
tabular-numson a data column, never writes aclamp()with aremterm, never setsline-break: strictfor CJK, never waits forcompositionendbefore firing validation. These are structural correctness issues, not style choices. - The agent reaches for physical CSS properties.
margin-left,padding-right,text-align: left— each one a quiet RTL breakage waiting to ship.
Read references/type-scale-and-rhythm.md first — the suite's technical core; for type, the axis that is load-bearing is the scale as a system (a decided ratio, fluid clamp(), semantic roles as tokens) rather than a pile of font-size declarations. Every gate here is a taste decision the agent cannot make for you — which ratio, which families, which density, how much i18n investment the surface needs; what it can do is enforce the system once you've set it.
Speak the user's language. Gloss a term on first use: modular scale / type ratio, fluid sizing / clamp(), measure / line-length, vertical rhythm / baseline grid, tabular numerals, OpenType features / font-variant-*, metrics-compatible fallback / size-adjust / no CLS, logical CSS properties / RTL-safe layout, grapheme cluster / why string.length lies, ICU MessageFormat / locale-correct pluralization. A system the user can't read is one imposed, not shared.
What ships with it
7 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.
- yesterday First seen · 136 lines · 234 tokens per session scan A 02de631d8350
type is a skill published in the GitHub repository IamK77/Skill (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 234 tokens to every session and 4,502 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
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
quick-recap
Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.