frontmatter-guardian

frontmatter-guardian is an agent for Codex from DailybotHQ/deepworkplan-skill. It costs 27 tokens per session (319 once invoked), scanned A, original, MIT.

An agent that checks and fixes the frontmatter—the metadata at the top of a file—in skills, agents, and command files.

In plain words
What is it for?
Use it after editing SKILL.md or related files to correct names, versions, documentation links, descriptions, and tool settings, then re-run validation.
Why use it?
It prevents metadata errors from failing the repository’s frontmatter validator.

Agent for Codex

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.

agentmods
npx agentmods add agents/dailybothq/deepworkplan-skill/frontmatter-guardian
Clone the repo
git clone --depth 1 https://github.com/DailybotHQ/deepworkplan-skill

Made for: Codex.

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-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/dailybothq/deepworkplan-skill/frontmatter-guardian.svg)](https://agentmods.dev/agents/dailybothq/deepworkplan-skill/frontmatter-guardian)
Your own site
<a href="https://agentmods.dev/agents/dailybothq/deepworkplan-skill/frontmatter-guardian"><img src="https://agentmods.dev/badge/agents/dailybothq/deepworkplan-skill/frontmatter-guardian.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.00319
Opus 5 $0.00014 $0.00160
Sonnet 5 $0.00005 $0.00064
Haiku 4.5 $0.00003 $0.00032

Measured 4d ago against content hash bba76e74254e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontmatter-guardian 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.

.agents/agents/frontmatter-guardian.md · 40 lines

What it actually says

Frontmatter Guardian

Role

Keeps every SKILL.md frontmatter conformant with the contract AGENTS.md §3 documents and scripts/validate-frontmatter.py enforces.

Inputs

A new or edited SKILL.md (or a request to audit all of them).

Process

  1. Run python3 scripts/validate-frontmatter.py and read its findings.
  2. For each violation, fix the frontmatter:
    • name: → kebab-case, starts with deepworkplan (never snake_case/camelCase)
    • version: → quoted SemVer string
    • replace any homepage: with documentation_url:
    • ensure description, user-invocable, allowed-tools are present and sane
  3. Never change the version number to satisfy the check — only fix quoting/format. The auto-release bot owns version numbers.
  4. Re-run the validator until it reports OK.

Output

The corrected frontmatter and a one-line note per file changed.

Notes

Scope is frontmatter only. The validator scans skills/ exclusively, so .agents/skills/* frontmatter follows the same house style by convention but is not CI-gated.

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. 4d ago First seen · 40 lines · 27 tokens per session scan A bba76e74254e

Subscribe to this mod's changes

frontmatter-guardian is an agent published in the GitHub repository DailybotHQ/deepworkplan-skill (20 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 319 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 2026-08-30.