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/chancegraff/rules-for-claude/archifynpx skills add chancegraff/rules-for-claude --skill archifygit clone --depth 1 https://github.com/chancegraff/rules-for-claudeWrote 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/chancegraff/rules-for-claude/archify)<a href="https://agentmods.dev/skills/chancegraff/rules-for-claude/archify"><img src="https://agentmods.dev/badge/skills/chancegraff/rules-for-claude/archify.svg" alt="Measured on agentmods" 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 | $0.00130 | $0.03374 |
| Opus 5 | $0.00065 | $0.01687 |
| Sonnet 5 | $0.00026 | $0.00675 |
| Haiku 4.5 | $0.00013 | $0.00337 |
Grade A, and why
archify 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.
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
60 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.
- assets/template.html 662 KB
- bin/archify.mjs 70 KB runs code
- bin/open-artifact.mjs 2.2 KB runs code
- bin/preview.mjs 23 KB runs code
- bin/visual-check.mjs 33 KB runs code
- brand-marks/catalog.json 14 KB
- brand-marks/README.md 1.4 KB
- delta/architecture-delta.mjs 71 KB runs code
- examples/agent-run.lifecycle.json 4.3 KB
- examples/agent-tool-call.workflow.json 5.6 KB
- examples/async-job-roundtrip.sequence.json 4.3 KB
- examples/brand-aware-delivery.architecture.json 3.2 KB
- examples/cache-miss-request.sequence.json 4.2 KB
- examples/checkout-platform.base.architecture.json 2.2 KB
- examples/checkout-platform.head.architecture.json 2.3 KB
- examples/dataflow-product-analytics.html 704 KB
- examples/deployment-release.lifecycle.json 4.2 KB
- examples/event-stream.dataflow.json 5.3 KB
- examples/incident-response.workflow.json 5.2 KB
- examples/lifecycle-agent-run.html 697 KB
- examples/product-analytics.dataflow.json 5.5 KB
- examples/production-deployment.architecture.json 5.3 KB
- examples/release-delivery.workflow.json 5.0 KB
- examples/sequence-cache-miss-request.html 700 KB
- examples/web-app-rendered.html 698 KB
- examples/web-app.architecture.json 3.7 KB
- examples/workflow-agent-tool-call-rendered.html 706 KB
- LICENSE 1.1 KB
- migrations/workflow-v2.mjs 9.0 KB runs code
- package.json 355 B
- recipes/scenarios.mjs 31 KB runs code
- references/authoring-contract.md 11 KB
- references/brand-marks.md 2.1 KB
- references/delivery-contract.md 7.9 KB
- references/viewer-runtime.md 4.1 KB
- renderers/architecture/grid.mjs 2.0 KB runs code
- renderers/architecture/render-architecture.mjs 44 KB runs code
- renderers/dataflow/README.md 4.1 KB
- renderers/dataflow/render-dataflow.mjs 21 KB runs code
- renderers/lifecycle/README.md 5.1 KB
- renderers/lifecycle/render-lifecycle.mjs 24 KB runs code
- renderers/sequence/README.md 4.7 KB
- renderers/sequence/render-sequence.mjs 21 KB runs code
- renderers/shared/brand-marks.mjs 22 KB runs code
- renderers/shared/cli.mjs 9.9 KB runs code
- renderers/shared/desktop-readability.mjs 1.1 KB runs code
- renderers/shared/diagnostics.mjs 4.5 KB runs code
- renderers/shared/engineering-profiles.mjs 6.8 KB runs code
- renderers/shared/generated-brand-marks.mjs 160 KB runs code
- renderers/shared/generated-validators.mjs 421 KB runs code
- renderers/shared/geometry.mjs 56 KB runs code
- renderers/shared/i18n.mjs 47 KB runs code
- renderers/shared/layout-report.mjs 1015 B runs code
- renderers/shared/legend.mjs 8.4 KB runs code
- renderers/shared/output-path.mjs 10 KB runs code
- renderers/shared/repository-evidence.mjs 11 KB runs code
- renderers/shared/text-fit.mjs 2.1 KB runs code
- renderers/shared/utils.mjs 11 KB runs code
- renderers/shared/validator.mjs 3.4 KB runs code
- renderers/workflow/README.md 10 KB
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 · 138 lines · 130 tokens per session scan A 10094272d6d1
archify is a skill published in the GitHub repository chancegraff/rules-for-claude (3 stars, last pushed today), with no licence file. It adds 130 tokens to every session and 3,374 once invoked, about $0.0006 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 2026-09-04.
Other skills, from other repositories
qa-check
Auto-detects the project's tech stack, then audits for Accessibility, Performance, and Code Quality. Works across WordPress/PHP, Python, Node/JS, and static web projects.
audit-vs-fix-discipline
Use when the user asks to audit, review, investigate, check, scan, "look at", or "find issues in" code — anything that sounds like a diagnostic request without an explicit fix authorization. Enforces findings-only output with severity tiering, forbids in-place fixes during audit, and blocks the…
figma
Figma-to-code workflow using MCP tools. Fetches design context, screenshots, variables, and Code Connect mappings before implementation.
module-depth-review
Use when reviewing whether module boundaries earn their keep — finding shallow modules that should be consolidated into deep ones. Triggers on phrases like "is this over-modularised?", "should these be one module?", "too many small files doing related work", "interface feels as complex as implementation", "review the…
swift-concurrency-review
Use when reviewing Swift 5.5+ code containing await, actor, Task { }, @MainActor, @unchecked Sendable, cancellable timer/deadline handles, or long-lived for await AsyncStream consumers — especially diffs extending existing actors with new methods. Catches post-await state-overwrite races, TOCTOU around Task spawn…
block-journey
Discover all files for a block or component, trace the editorial and front-end user journeys, and write a journey document to docs/journeys/.