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.
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsnpx agentmods add skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-skillWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-skill)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-skill"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-skill/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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-skill"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 40 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00028 | $0.06951 |
| Opus 5 | $0.00014 | $0.03476 |
| Sonnet 5 | $0.00006 | $0.01390 |
| Haiku 4.5 | $0.00003 | $0.00695 |
Grade A, and why
sk-create-skill 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 8d 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 — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Skill
create-skill is the skill-authoring workflow packet of the sk-doc parent hub. It owns standalone OpenCode skill scaffolding and parent-hub scaffolding through two workflow modes: create-skill and create-skill-parent.
1. WHEN TO USE
Activation Triggers
Use this packet when the request involves:
- Creating or rebuilding an OpenCode skill under
.opencode/skills/. - Running
/create:skillfor a standalone skill with its own advisor identity. - Running
/create:skill-parentfor a parent hub with nested workflow or surface packets. - Authoring or repairing
SKILL.md,README.md,references/,assets/,scripts/, orchangelog/for a skill package. - Creating parent-hub router files such as
mode-registry.json,hub-router.json,description.json, or hub-levelgraph-metadata.json. - Validating and packaging a skill with
scripts/package_skill.py.
Keyword triggers: create skill, /create:skill, /create:skill-parent, new skill, skill scaffold, SKILL.md scaffold, OpenCode skill, sk-skill, create sk-, reusable capability, reusable helper, starter reference docs, parent skill, parent hub, mode packet, nested workflow packet, package skill.
When NOT to Use
Use another sk-doc packet when:
- The user asks for agent scaffolding, command scaffolding, README or install-guide creation, benchmark packages, feature catalogs, manual testing playbooks, flowcharts, or changelogs. Use
create-agent,create-command,create-readme,create-benchmark,create-feature-catalog,create-manual-testing-playbook,create-flowchart, orcreate-changelog. - The task audits, validates, scores, or optimizes an existing skill document without authoring or rebuilding the skill. Use
create-quality-control. - The task is application code implementation. Route to
sk-code. - The user only needs conceptual advice and no artifact authoring or validation.
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/parent-skill/parent-skill-command-metadata-template.json 2.2 KB
- assets/parent-skill/parent-skill-description-template.json 1.5 KB
- assets/parent-skill/parent-skill-graph-metadata-template.json 3.7 KB
- assets/parent-skill/parent-skill-hub-router-template.json 6.7 KB
- assets/parent-skill/parent-skill-hub-template.md 15 KB
- assets/parent-skill/parent-skill-leaf-aliases-template.json 1000 B
- assets/parent-skill/parent-skill-readme-template.md 15 KB
- assets/parent-skill/parent-skill-registry-template.json 9.2 KB
- assets/parent-skill/parent-skill-root-router-template.md 6.7 KB
- assets/parent-skill/scaffold/hub-skill-scaffold.md 5.1 KB
- assets/parent-skill/scaffold/packet-skill-scaffold.md 2.9 KB
- assets/skill/skill-asset-template.md 26 KB
- assets/skill/skill-graph-metadata-template.json 1.6 KB
- assets/skill/skill-leaf-manifest-config-template.json 1.3 KB
- assets/skill/skill-md-template.md 39 KB
- assets/skill/skill-procedure-template.md 12 KB
- assets/skill/skill-readme-template.md 21 KB
- assets/skill/skill-reference-template.md 29 KB
- assets/skill/skill-scaffold-template.md 4.0 KB
- assets/skill/skill-smart-router.md 8.6 KB
- assets/skill/skill-sync-manifest-template.md 6.9 KB
- changelog/v1.0.0.0.md 2.2 KB
- changelog/v1.1.1.0.md 1.5 KB
- changelog/v1.2.0.0.md 2.8 KB
- manual-testing-playbook/manual-testing-playbook.md 12 KB
- manual-testing-playbook/parent-hub/author-a-two-axis-parent-hub.md 6.2 KB
- manual-testing-playbook/parent-hub/keep-one-parent-identity.md 5.6 KB
- manual-testing-playbook/parent-hub/keep-ready-separate-from-compiled-serving.md 6.0 KB
- manual-testing-playbook/standalone-skill/classify-standalone-root-metadata.md 6.0 KB
- manual-testing-playbook/standalone-skill/leave-quality-audits-alone.md 4.9 KB
- manual-testing-playbook/standalone-skill/scaffold-a-standalone-skill.md 6.3 KB
- README.md 12 KB
- references/parent-skill/compiled-routing-architecture.md 11 KB
- references/parent-skill/compiled-routing-lockstep-surfaces.json 3.0 KB
- references/parent-skill/parent-hub-router-schema.md 17 KB
- references/parent-skill/parent-skills-nested-packets.md 24 KB
- references/README.md 7.4 KB
- references/shared/advisor-index-handoff.md 8.1 KB
- references/shared/common-pitfalls.md 9.7 KB
- references/shared/overview.md 12 KB
- references/shared/skill-root-metadata-contract.md 14 KB
- references/shared/validation-and-packaging.md 6.8 KB
- references/skill/creation-workflow.md 19 KB
- references/skill/examples-and-maintenance.md 7.0 KB
- references/skill/upgrading-a-skill-to-v4.md 16 KB
- scripts/ci-leaf-manifest-freshness.cjs 8.4 KB runs code
- scripts/ci-router-vocabulary-reach.cjs 12 KB runs code
- scripts/ci-skill-derived-freshness.cjs 3.9 KB runs code
- scripts/ci-skill-root-metadata.cjs 27 KB runs code
- scripts/generate-leaf-manifest.cjs 15 KB runs code
- scripts/generate-router-intent-signals.cjs 4.8 KB runs code
- scripts/init_skill.py 34 KB runs code
- scripts/lib/command-metadata-schema.cjs 11 KB runs code
- scripts/lib/leaf-resource-contract.cjs 23 KB runs code
- scripts/lib/README.md 1.6 KB
- scripts/lib/root-router-contract.cjs 34 KB runs code
- scripts/lib/s-class-config-defaults.json 505 B
- scripts/lib/skill-root-metadata-contract.cjs 16 KB runs code
- scripts/package_skill.py 42 KB runs code
- scripts/README.md 2.0 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.
- 8d ago First seen · 471 lines · 28 tokens per session scan A 82cb35d01483
sk-create-skill is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 6,951 once invoked, about $0.0001 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…