Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/avengermojo/mojoassistant/agents-mdgit clone --depth 1 https://github.com/AvengerMoJo/MoJoAssistantWhat 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 | $0.00634 | $0.00634 |
| Opus 5 | $0.00317 | $0.00317 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
MoJoAssistant 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 2d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Operating Rules (Global in This Repo)
These rules apply to all coding agents working in this repository.
Source of Truth
- Primary policy document:
Coding Agents Rules.md - Agents should follow that file as the canonical rule set.
Configuration and Data Hierarchy
MoJoAssistant follows a Linux-style layered config convention. Agents must respect this:
| What | Where | Rule |
|---|---|---|
| System defaults, examples, templates | project/config/ |
Read-only at runtime. Never write here from running code. |
| Personal config overrides | ~/.memory/config/ |
User's personal layer. Wins over project defaults. |
| All personal data and runtime state | ~/.memory/ |
Conversations, knowledge, roles, task sessions, events — everything personal. |
| Secrets and environment | .env |
Never commit. Never hardcode. |
Simple rule for agents: when in doubt, ~/.memory/ is home. Read personal state from there. Write personal state there. project/config/ is factory defaults — read for fallback, never write at runtime.
Mandatory Memory Workflow
- Use MoJoAssistant MCP memory context to inform decisions before major edits.
- Persist important user/assistant exchanges and decisions to memory.
- Use memory context to self-correct and improve response quality over time.
Git Workflow
- Start work from
mainby creating a branch namedwip_<feature>(orwip_<feature_name>). - Keep implementation work on the
wip_<feature>branch until fully tested. - Merge into
mainonly when the user explicitly requests the merge. - All commits must be authored as the user, not as the agent.
- The user is accountable for committed code shared with community/company.
- Do NOT include
Co-Authored-Bylines in commit messages. The user is the sole author.
BRIDLE Validation Workflow (Core Principle)
Every state-changing action must prove it worked before moving on:
Act → Validate → Log → Dream → Learn → Correct
Three failure modes to never repeat:
- Fail without log — silent failure, same wall next run
- Log without learning — dreaming never ingests it, mistake repeats
- Mistake without correction — agent self-corrects silently, human never knows
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.
- 2d ago First seen · 56 lines · 634 tokens per session scan A bba31fb4f014
MoJoAssistant AGENTS.md is an instructions file published in the GitHub repository AvengerMoJo/MoJoAssistant (41 stars, last pushed 2mo ago), licensed MIT. It adds 634 tokens to every session, about $0.0032 per session on Opus 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.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.