agentmods.dev

metadata_mcp: Instructions file for Codex

AGENTS.md

metadata_mcp AGENTS.md is an instructions file for Codex, OpenCode from dullroar/metadata_mcp. It costs 588 tokens per session, scanned A, original, MIT.

Repository instructions for a coding agent working on a metadata service. Metadata is descriptive information about files, such as image details, audio tags or document properties.

In plain words
What is it for?
Use them when planning or implementing changes, selecting relevant documentation, updating design or memory files and deciding how to validate the work.
Why use it?
They tell the agent which project documents to read, how to resolve conflicting guidance and where different kinds of knowledge belong. This limits unnecessary context loading and keeps project records organized.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is dullroar/metadata_mcp's own configuration. It tells Codex and OpenCode how to work on metadata_mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything metadata_mcp configures →

not rated 0repo today A scan 588 tokens original MIT
View source ↗ dullroar/metadata_mcp
Reuse

Borrowing it

Nothing to install: this file belongs to dullroar/metadata_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dullroar/metadata_mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/dullroar/metadata_mcp

Made for: Codex, OpenCode.

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 metadata_mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dullroar/metadata_mcp/agents-md/github.svg)](https://agentmods.dev/instructions/dullroar/metadata_mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dullroar/metadata_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dullroar/metadata_mcp/agents-md/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 metadata_mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dullroar/metadata_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dullroar/metadata_mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 588 This file is loaded in full into every session.
When invoked 588 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00588 $0.00588
Opus 5.5 $0.00235 $0.00235
Sonnet 5.5 $0.00118 $0.00118
Haiku 4.5 $0.00059 $0.00059

Measured today against content hash f7e15143f6fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

metadata_mcp AGENTS.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 today.

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.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent contract

A FastMCP layer over established metadata engines (ExifTool, mutagen, Pandoc) and lightweight local probes.

Load context in this order

  1. Read this file.
  2. Read the short indexes in full: README.md, docs/README.md, memory/README.md, scripts/README.md.
  3. Match the task against each index's Read when entries and open only matching documents.
  4. For a large file, search its headings and read only the relevant ranges.
  5. Stop loading when the decision, intended files, constraints and validation method are known.

User instructions take precedence over repository guidance. When sources conflict, prefer: user instruction, this file, docs/design/, the named plan, domain documentation and references, memory/, implementation and tests, historical notes.

Context ownership

  • Universal rules belong here.
  • Architectural reasons belong in docs/design/ (one premise per file).
  • Non-obvious findings that cost time to discover belong in memory/ (one topic per file; edit the existing topic, do not append a rival).
  • Execution state belongs in plans/; deterministic automation in scripts/.
  • Every routed Markdown file starts with gist: "Read when: ..." front matter. Do not hand-edit the generated section of an index; run python scripts/build_context_indexes.py.

Do not duplicate a fact across layers. Correct its canonical source.

Planned work (spec-driven)

  • Work only on a named plan in plans/<plan>/ (spec.md plus steps/) or an explicitly identified off-plan task. Copy plans/TEMPLATE/ to start one.
  • Once its spec is approved, proceed through the steps without asking permission for routine work. Failed tests and dead ends inside scope: diagnose, repair, continue. Return to the user only for a new decision: contradictory requirements, scope expansion, or an action outside the spec's delegated authority.
  • Acceptance checks named in the spec are protected. Never weaken, skip or delete one to get green; if one cannot pass as written, escalate.
  • Parallel steps must have no dependency between them and no overlapping touches; if independence is uncertain, serialize. After parallel steps merge, run the spec's combined validation.
  • A step is done only with recorded evidence. Report unavailable verification honestly.
  • Retiring a rule, correcting documentation, and tolerating a known violation are different outcomes; record which one (see plans/TEMPLATE/spec.md).

Read the full file on GitHub · 43 lines

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. today First seen · 43 lines · 588 tokens per session scan A f7e15143f6fa

Subscribe to this mod's changes

metadata_mcp AGENTS.md is an instructions file published in the GitHub repository dullroar/metadata_mcp (0 stars, last pushed today), licensed MIT. It adds 588 tokens to every session, about $0.0024 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 2026-11-07.

Building agentsWriting and docs
Related

metadata_mcp AGENTS.md compared with instructions from other repositories

metadata_mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
metadata_mcp AGENTS.mddullroar/metadata_mcpInstructions file0todayMITA588Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode