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 skills/sliamh11/deus/add-editornpx skills add sliamh11/Deus --skill add-editorgit clone --depth 1 https://github.com/sliamh11/DeusWrote 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/skills/sliamh11/deus/add-editor)<a href="https://agentmods.dev/skills/sliamh11/deus/add-editor"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/add-editor.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.02824 |
| Opus 5 | $0.00044 | $0.01412 |
| Sonnet 5 | $0.00018 | $0.00565 |
| Haiku 4.5 | $0.00009 | $0.00282 |
Grade A, and why
add-editor 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 4d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Editor Integration (ACP / MCP)
Use Deus's memory and evolution layers from inside an external editor (or any MCP-capable client) by composing them onto the editor's own coding agent — you do not run Deus's container in the editor. The editor's agent keeps handling editor mechanics (diffs, permissions, buffers); Deus's two MCP servers supply the "brain":
deus-memory→memory_recall(semantic recall over your vault).deus-evolution→get_reflections/log_interaction/get_active_prompt/record_feedback(the reflexion loop).
This skill performs the wiring interactively. For the why (compose-not-port rationale,
caveats, why reflexion learns from mistakes not stated style), read
docs/EDITOR_INTEGRATION.md — do not duplicate that
reasoning here; just point the user at it if they ask.
Principle: when a precondition is missing, fix it (create the venv, pull the model). Only
pause for genuine user decisions (which editor, employer-machine containment, target project).
Use AskUserQuestion for every user-facing choice.
0. Scope — two independent parts
Tell the user this skill has two parts they can run independently:
- Machine-level editor config (steps 1-5) — wires the two MCP servers into the editor. Run once per machine.
- Per-project instruction file (step 6) — the close-the-loop
AGENTS.md. Run once per repo you want the loop active in.
If they only want one part, skip to it. Do not assume the directory you're invoked from is the project they want the loop in — step 6 asks explicitly.
1. Resolve the Deus repo root (absolute path)
The config below needs an absolute path to this Deus clone — some MCP clients do not expand
~, and on another machine (e.g. a work PC) the clone lives at a different path. Resolve it in
order and record it as ROOT:
git rev-parse --show-toplevel 2>/dev/null
- If that prints a path and it contains
scripts/deus-memory-mcp→ that'sROOT. - Else if
$HOME/deus/scripts/deus-memory-mcpexists →ROOT="$HOME/deus". - Else →
AskUserQuestion: "Where is your Deus repo cloned?" and use the answer.
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.
- 4d ago First seen · 234 lines · 89 tokens per session scan A 16e90508f47b
add-editor is a skill published in the GitHub repository sliamh11/Deus (51 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 2,824 once invoked, about $0.0004 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 skills, from other repositories
memcord
Privacy-first, self-hosted chat memory for OpenClaw — save and recall conversation history across sessions without any cloud dependency.
mem9
Persistent cloud memory for OpenClaw agents. Use when users say: "install mem9" "setup memory" "add memory plugin" "openclaw memory" "mem9 onboarding" "memory not working" "import memories" "upload sessions".
mem9
Persistent cloud memory for OpenClaw agents. Use when users say: "install mem9" "setup memory" "add memory plugin" "openclaw memory" "mem9 onboarding" "memory not working" "import memories" "upload sessions".
cortex
Personal knowledge compiler and memory system. Ingests raw sources (documents, notes, transcripts, captures) into a structured, interlinked knowledge base. Maintains living entity pages, learning analysis, and the MEMORY.md routing table. Replaces the librarian skill.
librarian
DEPRECATED — Use the cortex skill instead. Cortex v2 absorbs all librarian functionality (memory maintenance, knowledge organization, learning analysis) into a unified knowledge compiler. This skill is kept for backwards compatibility but all triggers now route to Cortex.
neuron-curated-memory
Use Neuron (the semantic-memory MCP server) the RIGHT way so its graph stays clean and useful. Before answering, load prior context; after answering, save a CURATED turn — 3-5 concept keywords (nouns/entities/tech, never verbs or filler), typed links with a short rationale, and never a self-link. This raises graph…