agentmods.dev

sdd-creator: Instructions file for Claude Code

AGENTS.md

sdd-creator AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from bezael/sdd-creator. It costs 2,820 tokens per session, scanned A, original, MIT.

Repository instructions for coding agents working on a plugin that distributes agent skills. They define naming, language, documentation, and project-structure rules, including how to add a new skill.

In plain words
What is it for?
Use them when editing documentation, adding skills, or changing the structure of the sdd-creator repository.
Why use it?
They give agents the local conventions needed to make changes that fit the repository and preserve the stated credits and language choices.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: ${CLAUDE_PLUGIN_ROOT} variable, but also the file is AGENTS.md. Also seen: mentions .claude-plugin; positional $N argument; mentions Claude Code.

This is bezael/sdd-creator's own configuration. It tells Claude Code, Codex and OpenCode how to work on sdd-creator 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 sdd-creator configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 18repo changed 16d ago A scan 2,820 tokens original MIT
View source ↗ bezael/sdd-creator
Reuse

Borrowing it

Nothing to install: this file belongs to bezael/sdd-creator. 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/bezael/sdd-creator/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/bezael/sdd-creator

Made for: Claude Code, 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 sdd-creator AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bezael/sdd-creator/agents-md"><img src="https://agentmods.dev/badge/instructions/bezael/sdd-creator/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,820 This file is loaded in full into every session.
When invoked 2,820 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 $0.02820 $0.02820
Opus 5.5 $0.01128 $0.01128
Sonnet 5.5 $0.00564 $0.00564
Haiku 4.5 $0.00282 $0.00282

Measured 16d ago against content hash b7b7709db5be, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdd-creator 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 16d 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.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — bezael/sdd-creator

This repo is a Claude Code marketplace (dominicode) with two plugins of Dominicode skills: dominicode-sdd-creator (engineering) and dominicode-marketing. It is also a Pi package. SDD (Spec-Driven Development) is an industry methodology — this repo distributes the Dominicode adaptation by Bezael Pérez, not the methodology's invention. Keep that framing in all docs and credits ("SDD adaptation by", never "methodology by").

CBRM (Contract Based Review Method) is Bezael Pérez's own named method, so its credit reads "CBRM by Bezael Pérez · Dominicode". Do not rewrite it as an adaptation, and do not rewrite SDD credits to match it.

The repo follows its own method: this file has the three CBRM parts, Contract, Lane and Verdict.

Contract

Work starts from a contract, never from a vague request. The contract is the list of acceptance criteria in the task's spec, and each criterion has the command that proves it.

  • Where the contract lives:
    • Features: specs/<slug>/spec.md + tasks.md, using the dominicode-sdd-creator skill. specs/INDEX.md lists every spec and the shared decisions.
    • Small Issues (clear bug, single-file change): a copy of .dominicode/spec.template.md at .dominicode/specs/<issue-number>-<slug>.md. Never fill the template in place.
  • No contract, no code. If the task has no acceptance criteria, write them and get them approved before touching code.
  • The contract is the only source of scope. If implementing it requires a decision the contract does not make, stop and update the contract first.

A task is done when:

  1. Every acceptance criterion has evidence: which command proves it and what its output was.
  2. The short loop and the long loop of the Lane pass, with no new reds.
  3. The diff contains nothing the contract did not request.

Point 3 is the one most often missed. Extra code is code without a contract.

Lane

The lane is where the agent is allowed to work and the harness it uses to check itself. Leaving the lane requires explicit permission.

Read the full file on GitHub · 184 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. 16d ago Changed · +100 lines · +1,340 tokens per session b7b7709db5be
  2. 25d ago Changed · +46 lines · +1,031 tokens per session 31382b797139
  3. 1mo ago First seen · 38 lines · 449 tokens per session scan A 84dcd8574e0b

Subscribe to this mod's changes

sdd-creator AGENTS.md is an instructions file published in the GitHub repository bezael/sdd-creator (18 stars, last pushed 16d ago), licensed MIT. It adds 2,820 tokens to every session, about $0.0113 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 2026-09-24.

Building agentsWriting and docs
Related

sdd-creator AGENTS.md compared with instructions from other repositories

sdd-creator AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sdd-creator AGENTS.mdbezael/sdd-creatorInstructions file1816d agoMITA2,820Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode