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/systemsnpx skills add IamK77/Skill --skill systemsgit 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 | $0.00223 | $0.04379 |
| Opus 5 | $0.00112 | $0.02190 |
| Sonnet 5 | $0.00045 | $0.00876 |
| Haiku 4.5 | $0.00022 | $0.00438 |
Grade A, and why
systems 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
systems
!checklist init ${CLAUDE_SKILL_DIR} --force
An atelier is a craftsman's studio — the place where the individual lenses (color, type, form, motion) are forged. systems is the workbench that holds them together: the skill that turns a set of well-chosen tokens into one coherent, non-drifting system by establishing the architecture that makes drift structurally impossible. Where the other lenses decide what the values are, systems decides where they live, how they cross every language boundary, and how they stay in sync — permanently. It runs across gated stages and will not advance past a GATE until the checklist tool clears it — order enforced, substance yours.
The governing fact: the design system is itself state, so it gets one source of truth. A CSS token file and a JS color object that both list the same palette are not two views of the same truth — they are two sources of truth, and the moment one is updated without the other, the surface is subtly two-toned, and no one knows why. The same law that surface:wellspring applies to application data (the design system is itself state, one source of truth) applies here to the design artifact: one source authors the tokens; every language reads from it. This is not a "keep things in sync" convention — it is the only architecture that does not rot under normal development velocity.
This is where the agent era bites:
- The agent re-types tokens per file and feels no wrongness. It will write
'#2563eb'in an inline style object,oklch(0.62 0.18 250)in a CSS file, andcolor.primary = '#2563eb'in atokens.ts— each plausible alone, the set a three-source system that will drift in three different directions within a sprint. It has no sense of the system degrading; the architecture must make the wrong thing impossible. - The agent treats a Figma file as the source of truth. It will generate code "to match the design" by reading screenshots and re-deriving values — reinventing, not consuming. Reinventing is the first step of drift. The token source is code; Figma is a downstream consumer.
- The agent reaches for prop explosion. Every component variation becomes a boolean flag:
<Button variant="..." size="..." iconLeft="..." ghost pill loading>. The combinations multiply; the component is unmaintainable. Composition over configuration is a structural decision, not a style preference — the agent will not make it without instruction. - The agent skips living documentation. It generates components without stories, without accessibility contracts, without a stability tier. The library appears to grow, but no one can consume it correctly, and no CI catches visual regressions. A library with no living documentation is a library that has already started to rot.
Read references/token-architecture-one-source.md first — the taxonomy, the three-layer architecture, the CSS↔JS boundary mechanics, and the IACVT footgun. For systems, the axis that is load-bearing: the single source of truth is an architectural decision, not a convention. The CSS↔JS boundary mechanics (the four options, the inline-style-beats-class-rules trap) are the encodable technique; deciding which source architecture fits the stack is the taste call that belongs to each gate. Load at the start; re-check at every gate.
This skill consumes the output of the other atelier lenses. Color, type, form, and motion each produce tokens as their delivered artifact. systems takes those tokens, places them in the three-layer architecture (raw → semantic → component), closes the CSS↔JS boundary, and makes the living library the single point of contact for everything downstream. Cross-reference surface:wellspring's law "the design system is itself state, one source of truth" — this skill is that law applied to the design artifact itself. Cross-reference surface:bulwark — it enforces the system at 1→N (the PR review pass that catches drift before it merges); its gate is only meaningful when systems has built the structure bulwark will protect.
What ships with it
6 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 · 125 lines · 223 tokens per session scan A ee4179beeb54
systems is a skill published in the GitHub repository IamK77/Skill (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 223 tokens to every session and 4,379 once invoked, about $0.0011 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.