Borrowing it
Nothing to install: this file belongs to saajunaid/caddis-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saajunaid/caddis-plugin/main/.github/instructions/document-frontmatter.instructions.mdgit clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/instructions/saajunaid/caddis-plugin/document-frontmatter)<a href="https://agentmods.dev/instructions/saajunaid/caddis-plugin/document-frontmatter"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/document-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/instructions/saajunaid/caddis-plugin/document-frontmatter"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/document-frontmatter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03804 | $0.03804 |
| Opus 5.5 | $0.01522 | $0.01522 |
| Sonnet 5.5 | $0.00761 | $0.00761 |
| Haiku 4.5 | $0.00380 | $0.00380 |
Grade A, and why
caddis-plugin document-frontmatter.instructions.md 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.
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Frontmatter Instructions
Apply this rule whenever you create or update a descriptive Markdown deliverable. The YAML frontmatter block must be the first content in the file, before the title, blockquotes, comments, or generated status headers.
This applies to outputs produced by planning, intent, preflight, relay, ADR, README, handoff, documentation, and report workflows, including outputs from writing-plans, intent-writer, preflight, relay, plan.prompt.md, adr.prompt.md, and create-readme.prompt.md.
Include frontmatter for:
- planning documents
- PRDs, ADRs, design docs, architecture docs, and requirements docs
- README files, runbooks, guides, reports, analyses, and handoffs
- status trackers, implementation notes, migration notes, and other prose-first Markdown artefacts
- session-spec / driver prompts (e.g.
.caddis/prompts/*.md) — they are generated deliverables with a lifecycle like any plan; usetype: prompt
The three tiers
caddis follows OKF-lite (Open Knowledge Format — the frontmatter layer only; the raw/ + +wiki/
restructure is deliberately skipped, see .caddis/parking-lot/kuns-tools-and-okf.md). As of OKF v0.2 the
schema is layered, and only the first tier is required:
| Tier | Fields | Rule |
|---|---|---|
| 0 — OKF core | type |
Required. The only field whose absence is a defect. |
| 1 — caddis provenance | status, feature, creation-agent, Original Author, Creation Date, Creating Model |
Expected on new documents authored through caddis workflows (the house convention below). |
| 2 — OKF v0.2 trust signals | stale_after, verified, generated |
Recommended. Add when the document has a re-verify horizon or has been confirmed by a human/hub. |
Backward compatibility is load-bearing. Every field added at v0.2 is optional and additive. A document that declares only
typeis valid. A document written before v0.2 — nostale_after, noverified, nogenerated, using thecreation-agent/Creating Modelfields — remains fully valid and must never be rewritten in bulk to adopt the new fields. Tooling treats a missing trust field as silence, not as an error.
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.
- 9d ago Changed · +4 lines · +72 tokens per session d3436287b16d
- 28d ago Changed · +37 tokens per session e8fe5cb6aad0
- 1mo ago Changed · +3 lines · +67 tokens per session b7e6bb622b31
- 1mo ago First seen · 273 lines · 3,628 tokens per session scan A 173e9ac558b0
caddis-plugin document-frontmatter.instructions.md is an instructions file published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 3,804 tokens to every session, about $0.0152 per session on Opus 5.5. 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.