frontmatter-parsing

frontmatter-parsing is a skill for Claude Code from a5c-ai/babysitter. It costs 40 tokens per session (1,951 once invoked), scanned A, original, MIT.

A parser and editor for YAML frontmatter, the structured metadata block at the top of a Markdown file. It works with planning documents and can read, validate, query, and update their fields.

In plain words
What is it for?
It helps extract individual fields, update planning metadata, validate frontmatter, and preserve the Markdown content below it.
Why use it?
It lets tools change metadata such as status, phase, dependencies, and modified files without rewriting the document body.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit It helps extract individual fields, update planning metadata, validate frontmatter, and preserve the Markdown content below it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a5c-ai/babysitter/frontmatter-parsing
About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,788 stars · on GitHub · a5c.ai

Install

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.

Any agent
npx skills add a5c-ai/babysitter --skill frontmatter-parsing
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

Made for: Claude Code.

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.

agentmods badge for frontmatter-parsing

README.md
[![agentmods](https://agentmods.dev/badge/skills/a5c-ai/babysitter/frontmatter-parsing/github.svg)](https://agentmods.dev/skills/a5c-ai/babysitter/frontmatter-parsing)
Your own site
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/frontmatter-parsing"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/frontmatter-parsing/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.

agentmods 80×15 button for frontmatter-parsing

Your own site · 80×15
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/frontmatter-parsing"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/frontmatter-parsing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,951 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.01951
Opus 5 $0.00020 $0.00975
Sonnet 5 $0.00008 $0.00390
Haiku 4.5 $0.00004 $0.00195

Measured 9d ago against content hash 8645d6d93d25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

frontmatter-parsing 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 9d 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.

library/methodologies/gsd/skills/frontmatter-parsing/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

status: in-progress phase: 72 wave: 1 depends_on: [] files_modified: ["src/auth/oauth.ts", "src/auth/tokens.ts"] created: 2026-03-02 updated: 2026-03-02

Plan content below...


## Capabilities

### 1. Parse Frontmatter

Extract frontmatter from a markdown file into structured data:

```yaml
# Input file: .planning/phase-72/PLAN-1.md
---
status: planned
phase: 72
plan_number: 1
wave: 1
depends_on: []
files_modified:
  - src/auth/oauth.ts
  - src/auth/tokens.ts
  - src/middleware/auth.ts
task_count: 4
created: 2026-03-02
gap_closure: false
---

Parsed result:

{
  "status": "planned",
  "phase": 72,
  "plan_number": 1,
  "wave": 1,
  "depends_on": [],
  "files_modified": ["src/auth/oauth.ts", "src/auth/tokens.ts", "src/middleware/auth.ts"],
  "task_count": 4,
  "created": "2026-03-02",
  "gap_closure": false
}

2. Extract Specific Fields

Read individual fields without parsing the entire frontmatter:

get_field(.planning/phase-72/PLAN-1.md, "wave") -> 1
get_field(.planning/phase-72/PLAN-1.md, "status") -> "planned"
get_field(.planning/phase-72/PLAN-1.md, "files_modified") -> ["src/auth/oauth.ts", ...]

3. Update Fields

Update individual frontmatter fields without modifying body content:

update_field(.planning/phase-72/PLAN-1.md, "status", "executed")
update_field(.planning/phase-72/PLAN-1.md, "wave", 2)
update_field(.planning/phase-72/PLAN-1.md, "updated", "2026-03-02")

Uses Edit tool to surgically replace only the target field line.

4. Add New Fields

Add fields to existing frontmatter:

add_field(.planning/phase-72/PLAN-1.md, "executed_at", "2026-03-02T14:30:00Z")
add_field(.planning/phase-72/PLAN-1.md, "executor_agent", "gsd-executor")

Inserts new field before the closing --- delimiter.

5. Remove Fields

Remove fields from frontmatter:

remove_field(.planning/phase-72/PLAN-1.md, "gap_closure")

6. Query Across Files

Find documents matching frontmatter criteria:

query(directory: ".planning/phase-72/", field: "wave", value: 1)
-> [".planning/phase-72/PLAN-1.md", ".planning/phase-72/PLAN-2.md"]

Read the full file on GitHub · 248 lines

Files

What ships with it

1 file 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.

  1. 9d ago First seen · 248 lines · 40 tokens per session scan A 8645d6d93d25

Subscribe to this mod's changes

frontmatter-parsing is a skill published in the GitHub repository a5c-ai/babysitter (1,788 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 1,951 once invoked, about $0.0002 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.