agentmods.dev

mistermorph: Instructions file for Codex

AGENTS.md

mistermorph AGENTS.md is an instructions file for Codex, OpenCode from quailyquaily/mistermorph. It costs 989 tokens per session, scanned A, original, Apache-2.0.

A repository guide for the MisterMorph coding project. It explains the code layout, configuration, build and test commands, console app, demos, and connections to other coding agents.

In plain words
What is it for?
Building and testing MisterMorph, finding the right modules, running its command-line tool, working on the web console or embedding demos, and using its configured tools and providers.
Why use it?
It gives an agent the project-specific rules and commands it needs to work safely, instead of guessing how the repository is organized or checked.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions Codex.

This is quailyquaily/mistermorph's own configuration. It tells Codex and OpenCode how to work on mistermorph 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 mistermorph configures →

not rated 83repo +1 changed 1mo ago A scan 989 tokens original Apache-2.0
View source ↗ quailyquaily/mistermorph mistermorph.com
Reuse

Borrowing it

Nothing to install: this file belongs to quailyquaily/mistermorph. 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/quailyquaily/mistermorph/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/quailyquaily/mistermorph

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 mistermorph AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/quailyquaily/mistermorph/agents-md"><img src="https://agentmods.dev/badge/instructions/quailyquaily/mistermorph/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 989 This file is loaded in full into every session.
When invoked 989 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 $0.00989 $0.00989
Opus 5.5 $0.00396 $0.00396
Sonnet 5.5 $0.00198 $0.00198
Haiku 4.5 $0.00099 $0.00099

Measured 1mo ago against content hash e47bd7fbf958, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mistermorph 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 1mo 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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

  • cmd/mistermorph/: CLI entrypoint and subcommands.
  • agent/: agent engine (loop, parsing, prompts, logging).
  • llm/: shared LLM types/interfaces used by the agent and providers.
  • providers/: LLM backends (currently providers/uniai/).
  • tools/ and tools/builtin/: tool registry and built-ins (web_search, url_fetch, bash, read_file).
  • skills/: skill discovery and selection logic for SKILL.md.
  • demo/: embedding examples (demo/embed-go/, demo/embed-cli/).
  • wrappers/acp/: optional stdio bridges for external ACP agents (Codex app-server, Claude Code print mode, Cursor CLI agent acp proxy).
  • Root configs: assets/config/config.example.yaml (template) and config.yaml (local). mistermorph in repo root is a build artifact.

Build, Test, and Development Commands

  • Build: go build -o ./bin/mistermorph ./cmd/mistermorph
  • Run (no build): go run ./cmd/mistermorph --help
  • Test: go test ./...
  • Static checks: go vet ./...
  • Example run:
    • ./bin/mistermorph run --task "Summarize this repo" --provider openai --model gpt-5.2 --api-key "$OPENAI_API_KEY"

Console Frontend (web/console)

  • Package manager: use pnpm (do not use npm).
  • Allowed commands:
    • pnpm install
    • pnpm add <pkg>
    • pnpm dev
    • pnpm build

Demos (Embedding)

  • Go library demo: cd demo/embed-go && OPENAI_API_KEY="..." go run . --task "List files and summarize."
  • CLI subprocess demo: go build -o ./bin/mistermorph ./cmd/mistermorph, then cd demo/embed-cli && MISTER_MORPH_BIN=../../bin/mistermorph OPENAI_API_KEY="..." go run . --task "Search for OpenAI and fetch the first result"
  • Both demos require network access (OpenAI-compatible provider).

Coding Style & Naming Conventions

  • Format Go code with gofmt (go fmt ./... is fine for day-to-day).
  • Package names are lowercase; exported identifiers use PascalCase; locals use camelCase.
  • Keep provider-specific behavior in providers/<name>/ and avoid leaking it into agent/.

Read the full file on GitHub · 71 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. 1mo ago Changed · +6 lines · +137 tokens per session e47bd7fbf958
  2. 2mo ago First seen · 65 lines · 852 tokens per session scan A 3fe0bdf00404

Subscribe to this mod's changes

mistermorph AGENTS.md is an instructions file published in the GitHub repository quailyquaily/mistermorph (83 stars, last pushed yesterday), licensed Apache-2.0. It adds 989 tokens to every session, about $0.0040 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 2026-08-30.

Goagent-libraryai-agents
Related

mistermorph AGENTS.md compared with instructions from other repositories

mistermorph AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mistermorph AGENTS.mdquailyquaily/mistermorphInstructions file83yesterdayApache-2.0A989Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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