agentmods.dev

aegis AGENTS.md

Repository instructions for Aegis, covering how to run its terminal interface, web app, headless server, logs, configuration commands, and related project knowledge.

In plain words
What is it for?
Use them when running Aegis, viewing logs, creating configuration files, or working with its terminal and web interfaces.
Why use it?
They explain which command to use for local, remote, or headless operation and where to find the project's operating guidance.

Instructions file for CodexOpenCode

20 5d ago A scan 12,475 tokens original MIT
View the source file apiad/aegis
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/apiad/aegis/agents-md
Clone the repo
git clone --depth 1 https://github.com/apiad/aegis

Made for: Codex, OpenCode.

Per session 12,475 This file is loaded in full into every session.
When invoked 12,475 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.12475 $0.12475
Opus 5 $0.06237 $0.06237
Sonnet 5 $0.02495 $0.02495
Haiku 4.5 $0.01247 $0.01247

Measured 2d ago against content hash 64eeef6027f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aegis 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.

AGENTS.md · 724 lines

How it starts

The opening of the file, as written. The whole thing — 724 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents

Running

aegis                         # full-screen TUI — first-class UI for
                              # local dev (opens ConfigPanel when
                              # there's no .aegis.yaml)
aegis web                     # installable PWA — first-class UI for
                              # remote (and local) dev; ensures a token,
                              # opens the browser, serves the web client
aegis serve                   # headless: MCP plane + web frontend
aegis logs [-c] [-f]          # the aegis process log — what the harness
                              # itself did, and the crashes it recorded
                              # on its way down (-c = crashes only)
aegis config ...              # scriptable .aegis.yaml authoring
                              # (agent / harness / queue / default-agent
                              #  / plugin-dir / show)

The TUI and the web/PWA client are two co-equal first-class UIs over one aegis serve backend: the TUI for local dev, the web client for remote dev over a flaky link (mobile-first, installable) and local dev too. Both render the same transcripts with the same fidelity.

Know-how

Procedure docs under know-how/ — match the task, load the doc before acting:

  • know-how/deploying-web.md — reach for it when deploying / redeploying / debugging the public aegis web UI (dev.apiad.net) on the VPS.
  • know-how/native-lovelaice-agent.md — reach for it when working on the native (harness-free) lovelaice agent / driver: config, MCP injection, streaming, resume, cancel, and the real-model-probe discipline.
  • know-how/remote-tui.md — reach for it when running the TUI against a remote or auto-launched aegis serve (via --remote ws://… or ssh://…), or debugging the WS client / SSH tunnel path.
  • know-how/releasing.md — reach for it when cutting a release / bumping the version / pushing a vX.Y.Z tag — especially the uv.lock re-lock gate that has failed the PyPI publish twice.
  • know-how/ssh-execution-hosts.md — reach for it when configuring or debugging a hosts: entry — a session whose harness runs on another machine (/spawn main@vps) — or the SSH ControlMaster / reverse MCP tunnel behind it. Distinct from --remote and from remotes:.

Read the full file on GitHub · 724 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 · 724 lines · 12,475 tokens per session scan A 64eeef6027f5

Subscribe to this mod's changes

aegis AGENTS.md is an instructions file published in the GitHub repository apiad/aegis (20 stars, last pushed 5d ago), licensed MIT. It adds 12,475 tokens to every session, about $0.0624 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.

agentic-aiharnessmcppython3textualtui
Related

Other instructions, from other repositories

mini-swe-agent AGENTS.md

Instructions for SWE-agent/mini-swe-agent, covering mini-swe-agent overview, style guide, bad, good and test style.

SWE-agent/mini-swe-agent · 975 tokens

mini-swe-agent copilot-instructions.md

Instructions for SWE-agent/mini-swe-agent, covering style guide, test style, bad and good.

SWE-agent/mini-swe-agent · 378 tokens

trueforge AGENTS.md

Instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.

truefoundry/trueforge · 1,070 tokens

sidecar AGENTS.md

Instructions for marcus/sidecar, covering working with td, markdown plans, commit completed work by default, working inside a sidecar shell and demoing features.

marcus/sidecar · 2,978 tokens

clawock AGENTS.md

Instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.

KCNyu/clawock · 2,140 tokens

clawock CLAUDE.md

Instructions for KCNyu/clawock, covering claude.md, identity & user, required reads (every session, in order), what lives where and cron run loop (what openclaw fires).

KCNyu/clawock · 867 tokens