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/vtemian/micode/claude-mdgit clone --depth 1 https://github.com/vtemian/micodeWhat 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 | $0.01574 | $0.01574 |
| Opus 5 | $0.00787 | $0.00787 |
| Sonnet 5 | $0.00315 | $0.00315 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
micode CLAUDE.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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Micode: Project Rules
Writing
- Never use em dashes. Use colons, commas, or parentheses for asides, and restructure sentences that rely on em dashes.
Code Style
- No classes for business logic. Use factory functions (
createX) with closed-over state - No nesting beyond 2 levels inside a function body. Prefer early returns and small helpers
- Max function length: 40 lines (skipBlankLines, skipComments)
- No magic numbers/strings. Use named constants. Place shared tunables in
src/utils/config.ts - No
anytypes. Minimize type assertions (as Type): prefer Valibot schemas or type guards to narrow. Assertions are acceptable when the plugin SDK's loose typing leaves no alternative - Use
unknownat system boundaries and normalize with Valibot orextractErrorMessage(...)before handling - No comments explaining what, only why when non-obvious
- Double quotes, semicolons, trailing commas (enforced by Biome)
- Max cognitive complexity: 10 per function (enforced by sonarjs)
- No duplicate string literals beyond 3 occurrences (enforced by sonarjs)
- No nested ternaries (enforced by unicorn)
- 2-space indent, 120-char line width, bracket spacing, always-parenthesized arrow functions (enforced by Biome)
- All promises must be awaited or explicitly handled; no floating promises
Architecture
Module Layout
src/agents/- Agent configuration objects (pure data, no logic). Each exports anAgentConfigsrc/hooks/- Lifecycle hook factories:createXHook(ctx: PluginInput) => { handlers }. All receivectx: PluginInputfor dependency injectionsrc/tools/- Bun tool definitions via the plugin'stool()function from@opencode-ai/plugin/toolsrc/utils/- Shared utilities:config.ts(centralized tunables),errors.ts(error extraction),logger.ts(structured logging),model-limits.ts(context window limits)src/config-loader.ts- Loads and validates micode.json/opencode.json configuration, merges agent overridessrc/mindmodel/- Project-specific coding pattern constraints (.mindmodel/ directory): loader, classifier, formatter, reviewsrc/octto/- Browser-based brainstorming UI:session/(WebSocket lifecycle),state/(branch persistence),ui/(HTML bundle)src/indexing/- Milestone artifact classification and ingestion for thoughts/ searchthoughts/- Persistent artifact storage:ledgers/(session continuity),shared/plans/andshared/designs/(outputs)
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 · 109 lines · 1,574 tokens per session scan A 9211ea724e76
micode CLAUDE.md is an instructions file published in the GitHub repository vtemian/micode (472 stars, last pushed 8d ago), licensed MIT. It adds 1,574 tokens to every session, about $0.0079 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.
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.
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).
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.