A routing skill for coding work that combines quality checks, code review, and project-specific guidance for Webflow, OpenCode, Pi Remote, and Obsidian codebases. It detects the relevant project surface and programming language before applying its workflow.

Use it for code-family tasks such as implementing features, reviewing changes, debugging, and running project-specific quality checks.

It helps an agent use the right implementation, debugging, review, and verification rules for the code it is changing.

sk-code — Skill for Claude Code and OpenCode by MichelKerkmeester

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loops

agentmods

npx agentmods add skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code

Made for: Claude Code, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code/github.svg)](https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code)

Your own site

<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,317 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00094	$0.03317
Opus 5	$0.00047	$0.01658
Sonnet 5	$0.00019	$0.00663
Haiku 4.5	$0.00009	$0.00332

Measured 6d ago against content hash 6fffa1f2fe6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sk-code 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 6d 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.

.opencode/skills/sk-code/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Family Hub (sk-code)

One skill, two axes, one shared surface-detection router, and one advisor identity. The workflow axis is two code modes that act (sk-code-quality, sk-code-review); the surface axis is four read-only evidence packets the hub bundles alongside a workflow mode (sk-code-webflow, sk-code-opencode, sk-code-mobile-cli, sk-code-obsidian). Each surface carries the shared implement → debug → verify workflow doctrine (shared/references/workflow_*.md, symlinked in) plus its own stack knowledge; sk-code-webflow also carries the folded-in Motion.dev animation overlay. This hub holds NO per-mode logic: it routes by workflowMode through mode-registry.json, and each mode or surface keeps its own contract in its packet.

1. WHEN TO USE

Use this skill for code-family workflows. Invoke it as sk-code with an optional mode hint such as quality: <request>; the hub classifies the request, resolves a mode key, and loads the matching nested packet.

Workflow axis (modes that act — one is chosen as primary):

Mode	Use it for	Packet
sk-code-quality	Quality gate; P0/P1/P2 author checks; comment hygiene; surface checklists.	`sk-code/sk-code-quality/`
sk-code-review	Findings-first review; security/correctness baseline; checklists; output contract; PR-state gates.	`sk-code/sk-code-review/`

Surface axis (read-only evidence the hub bundles alongside the primary mode — never a primary, advisor-invisible):

Surface	Carries	Packet
sk-code-webflow	Frontend evidence: CSS/HTML/JS standards, implementation and performance patterns, CDN deployment, browser debug/verify — plus the Motion.dev animation overlay. Bundles the implement → debug → verify workflow doctrine (read-only evidence) for the Webflow surface; the acting agent applies it.	`sk-code/sk-code-webflow/`
sk-code-opencode	System-code evidence: TypeScript/Python/shell/config standards, hooks, alignment verification, authoring checklists. Bundles the implement → debug → verify workflow doctrine (read-only evidence) for the OpenCode surface; the acting agent applies it.	`sk-code/sk-code-opencode/`
sk-code-mobile-cli	Svelte design-system and source-convention evidence for the Pi Remote Mobile-CLI app. Read-only.	`sk-code/sk-code-mobile-cli/`
sk-code-obsidian	Obsidian-plugin design-system and source-convention evidence for the Note Database plugin. Read-only.	`sk-code/sk-code-obsidian/`

Read the full file on GitHub · 198 lines

Files

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.

Changes

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.

6d ago First seen · 198 lines · 94 tokens per session scan A 6fffa1f2fe6c

Subscribe to this mod's changes

sk-code is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 3,317 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 2026-09-03.

Code review Debugging

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

gsd-ns-review

Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.

open-gsd/gsd-core · 16 tokens

issue

Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…

jeremylongshore/tons-of-skills-marketplace · 115 tokens

sk-code