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 skills add MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill sk-create-frontmattergit clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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-frontmatter)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-frontmatter"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-frontmatter/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-frontmatter"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-frontmatter.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 Prompt Injection · line 8 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00000 | $0.03161 |
| Opus 5 | $0.00000 | $0.01580 |
| Sonnet 5 | $0.00000 | $0.00632 |
| Haiku 4.5 | $0.00000 | $0.00316 |
Grade A, and why
sk-create-frontmatter 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 4d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-frontmatter
create-frontmatter is the frontmatter workflow packet of the sk-doc family. It owns
the contract every other mode writes against: which fields a document class carries, what
each field may contain, and how the 4-part version field is derived and inserted.
Six sibling modes emit frontmatter. None of them decides what a frontmatter block is. This mode does, and they cite it.
This mode owns rules, not enforcement. The validators and the versioning engine live in the hub's shared tier because a post-edit hook outside this hub resolves them by path. This mode is where you find out what the validators are checking for and why.
1. WHEN TO USE
Activation Triggers
- A document needs a frontmatter block and you do not know which fields its class carries.
- A validator rejected a frontmatter block and the message names a field rather than a fix.
- A
descriptionis over budget and needs trimming without losing its routing signal. - A
versionfield needs deriving, inserting or reconciling against a changelog anchor. - Someone asks what
trigger_phrases,importance_tierorcontextTypeare for. - A document class is being added and needs a frontmatter rule of its own.
Keyword triggers: yaml frontmatter, frontmatter block, frontmatter template, frontmatter field, frontmatter fields, trigger_phrases, trigger phrases, importance_tier, contextType, description budget, 4-part version, X.Y.Z.W, frontmatter versioning, frontmatter version, version field, frontmatter validation, missing frontmatter, frontmatter contract, yaml header, goes at the top of the file, version number at the top, importance tier, versioning pass, stopped showing up in suggestions, validator says my file is missing, description too long, edit count, field the validator wants.
What ships with it
20 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/fixtures/over-budget-description.md 2.5 KB
- assets/fixtures/README.md 1.7 KB
- assets/fixtures/under-budget-trim-lost-tokens.md 1.7 KB
- assets/frontmatter-templates.md 41 KB
- changelog/v1.0.0.0.md 3.9 KB
- manual-testing-playbook/description-budget/silent-discovery-drop.md 9.0 KB
- manual-testing-playbook/description-budget/trim-an-over-budget-description.md 9.6 KB
- manual-testing-playbook/description-budget/trim-that-loses-routing-tokens.md 9.3 KB
- manual-testing-playbook/field-and-class-resolution/author-a-reference-block.md 10 KB
- manual-testing-playbook/field-and-class-resolution/class-row-before-field-row.md 8.7 KB
- manual-testing-playbook/field-and-class-resolution/out-of-scope-class.md 7.8 KB
- manual-testing-playbook/manual-testing-playbook.md 27 KB
- manual-testing-playbook/version-derivation/changelog-anchored-derivation.md 8.7 KB
- manual-testing-playbook/version-derivation/idempotent-rerun.md 8.8 KB
- manual-testing-playbook/version-derivation/no-frontmatter-is-skipped.md 8.4 KB
- manual-testing-playbook/version-derivation/numstat-gate.md 8.5 KB
- manual-testing-playbook/version-derivation/skip-on-differ.md 8.5 KB
- README.md 13 KB
- references/frontmatter-versioning.md 10 KB
- references/README.md 1.4 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.
- 4d ago Changed · +21 lines 2b07dacf2276
- 6d ago Changed · +5 lines a4e1a01a9754
- 8d ago First seen · 219 lines · 0 tokens per session scan A 5af95ced2b47
sk-create-frontmatter is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,161 tokens. 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.