comis AGENTS.md

Repository-wide instructions for coding agents working on Comis, a software project. They describe its architecture, package layout, engineering rules, and approved extension points.

In plain words
What is it for?
Understanding Comis packages, adding features through port interfaces, implementing adapters, and wiring them into the application bootstrap.
Why use it?
They give agents a consistent way to change the code without bypassing the project's design or scattering changes across unrelated parts.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/comisai/comis/agents-md
Clone the repo
git clone --depth 1 https://github.com/comisai/comis

Made for: Codex, OpenCode.

Per session 13,563 This file is loaded in full into every session.
When invoked 13,563 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.13563 $0.13563
Opus 5 $0.06782 $0.06782
Sonnet 5 $0.02713 $0.02713
Haiku 4.5 $0.01356 $0.01356

Measured 2d ago against content hash e1851f207862, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comis 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.

Origin

This is a copy

86% identical to gomaa AGENTS.md — 455 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Comis Engineering Protocol

Default working protocol for coding agents. Scope: entire repository.

1) Architecture

Hexagonal (ports + adapters). Core defines port interfaces; adapters implement them; everything is wired via AppContainer in packages/core/src/bootstrap.ts (composition root). Extending Comis means implementing a port interface and wiring it in bootstrap — not cross-cutting rewrites.

Extension points in packages/core/src/:

  • ports/ — port interfaces (*Port suffix): ChannelPort, ChannelPluginPort, MemoryPort, SkillPort, EmbeddingPort, MediaResolverPort, TranscriptionPort, TTSPort, ImageAnalysisPort, VisionPort, FileExtractionPort, OutputGuardPort, SecretStorePort, DeviceIdentityPort, CredentialMappingPort, PluginPort, DeliveryQueuePort, DeliveryMirrorPort, ClockPort, EnvPort, TimerPort (+ TimerHandle), ContextStorePort, SessionStorePort, FileLockPort, CapabilityServiceControlPort, ManagedRunStorePort, ManagedRunContentPort, WorkspaceLeasePort, ExecutionAttachmentPort, hook types. Adapters live in the consumer package (e.g., @comis/memory for store ports) or @comis/infra for runtime adapters (createSystemClock, createSystemEnv, createSystemTimers).
  • runtime/ — sanctioned-root in-package helpers (system-time.ts: systemNowMs, systemNowDate, systemDateFrom, systemSleep, systemSetTimeout/systemClearTimeout, systemSetInterval/systemClearInterval, systemScheduleTimeout, systemGetEnv, systemEnvSnapshot). Use these only at trust-boundary call sites that genuinely cannot accept an injected port (top-level loggers, OAuth poll loops). Secrets must still go through SecretManager.
  • domain/ — Zod-validated domain types (NormalizedMessage, MemoryEntry, AgentResponse, ExecutionGraph, SubagentResult, ApprovalRequest, CredentialMapping, SecretRef, etc.). Define schema → infer type with z.infer.
  • security/ — security primitives: safePath, validateUrl (SSRF), SecretManager, SecretsCrypto (AES-256-GCM), ScopedSecretManager, SecretRefResolver, ActionClassifier, AuditAggregator, InputSecurityGuard, validateInput, OutputGuard, MemoryWriteValidator, wrapExternalContent, sanitizeLogString, CanaryToken, injection patterns + rate limiter.
  • config/ — Zod schemas, layered config (defaults → YAML files → env overrides). Paths via COMIS_CONFIG_PATHS (comma-separated). Runtime writes use config.patch / config.apply, while immutable topology is changed in config files and applied on restart; docs/reference/config-yaml.mdx owns the field contracts.
  • event-bus/TypedEventBus with strongly-typed event families including AgentEvents, ChannelEvents, MessagingEvents, InfraEvents, CapabilityServiceEvents, and ManagedRunEvents. Logging supplements events, does not replace them.
  • hooks/PluginRegistry + HookRunner for plugin lifecycle.
  • context/ — AsyncLocalStorage request-scoped context via runWithContext() / getContext().
  • bootstrap.ts — composition root → AppContainer.

Read the full file on GitHub · 408 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. 2d ago First seen · 408 lines · 13,563 tokens per session scan A e1851f207862

Subscribe to this mod's changes

comis AGENTS.md is an instructions file published in the GitHub repository comisai/comis (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13,563 tokens to every session, about $0.0678 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to gomaa AGENTS.md, differing in 455 lines, and is treated as a copy.