Borrowing it
Nothing to install: this file belongs to jungjaehoon-lifegamez/MAMA. 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/jungjaehoon-lifegamez/MAMA/main/AGENTS.mdgit clone --depth 1 https://github.com/jungjaehoon-lifegamez/MAMAWrote 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/jungjaehoon-lifegamez/mama/agents-md)<a href="https://agentmods.dev/instructions/jungjaehoon-lifegamez/mama/agents-md"><img src="https://agentmods.dev/badge/instructions/jungjaehoon-lifegamez/mama/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.
<a href="https://agentmods.dev/instructions/jungjaehoon-lifegamez/mama/agents-md"><img src="https://agentmods.dev/badge/instructions/jungjaehoon-lifegamez/mama/agents-md.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 | $0.03377 | $0.03377 |
| Opus 5.5 | $0.01351 | $0.01351 |
| Sonnet 5.5 | $0.00675 | $0.00675 |
| Haiku 4.5 | $0.00338 | $0.00338 |
Grade B, and why
MAMA AGENTS.md scanned grade B with 1 finding 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 10d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `--setting-sources` | `project,local` (no `user`) | Keeps `~/.claude/settings.json` plugins out | How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Shared instructions for every coding agent working in this repository (Claude Code, Codex, and
others). Claude-only notes live in CLAUDE.md.
Purpose first
- Read INTENT.md before starting or resuming work. Tie every plan and change to one of its owner checks (recognise, attach, answer, report, learn) or to the shared-engine goal.
- The product is "Kagemusha's loop + a wiki + memory that carries over". What sets it apart is task history and similar-case search. Team features wait until the owner flow works on real data.
- Work is done when real owner questions on real data get the right answer. Passing tests, structure checks, line or file counts, and progress scripts are supporting evidence only. Never report a finished sub-task as the purpose being met.
- The current work list is docs/development/plan.md. After each item, add 3–5
lines to docs/development/checks.md: result, evidence, what still fails.
Both are working documents: commit them straight to
main, without a PR (owner, 2026-10-06). - What a better model would fix is not product work. A problem counts only when a perfect model could not solve it with today's tools, data and write paths. A done condition checks what the program delivers, not whether the model obeys it (owner, 2026-10-06).
Repository map
| Package | Role |
|---|---|
packages/mama-core |
Shared engine: storage, records with revisions, search, embeddings, memory, raw observations, runtime, action catalog. Used by MAMA and by other projects |
packages/standalone |
Product (MAMA OS, mama CLI): connectors, owner loop, tasks/board/wiki/reports, viewer |
packages/mcp-server |
Public MCP server (plain JS) for Claude Code / Desktop |
packages/claude-code-plugin |
Claude Code plugin (hooks, commands) for development-session memory |
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.
- 10d ago Changed · +1 lines · +25 tokens per session a6cf55f13284
- 11d ago Changed · +7 lines · +148 tokens per session 211403ec7c45
- 14d ago Changed · +9 lines · +159 tokens per session 331242042b4d
- 17d ago Changed · +11 lines · +270 tokens per session 79b3d26b8e43
- 18d ago Changed · +7 lines · +106 tokens per session 6c90ce59d386
- 20d ago Changed · +6 lines · +133 tokens per session 960e1e7394cf
- 22d ago Changed · +4 lines · +70 tokens per session 10ace672ce5d
- 23d ago Changed · +6 lines · +98 tokens per session f10cbf445a74
- 29d ago Changed · -282 lines · -2,005 tokens per session 1f790cb110fc
- 1mo ago First seen · 430 lines · 4,373 tokens per session scan B 1c39dfcbf5bf
MAMA AGENTS.md is an instructions file published in the GitHub repository jungjaehoon-lifegamez/MAMA (14 stars, last pushed 10d ago), licensed MIT. It adds 3,377 tokens to every session, about $0.0135 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
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).