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 skills add carsteneu/yesmem --skill yesmem-agentsgit clone --depth 1 https://github.com/carsteneu/yesmemWrote 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/carsteneu/yesmem/yesmem-agents)<a href="https://agentmods.dev/skills/carsteneu/yesmem/yesmem-agents"><img src="https://agentmods.dev/badge/skills/carsteneu/yesmem/yesmem-agents/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/carsteneu/yesmem/yesmem-agents"><img src="https://agentmods.dev/badge/skills/carsteneu/yesmem/yesmem-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00043 | $0.00706 |
| Opus 5 | $0.00022 | $0.00353 |
| Sonnet 5 | $0.00009 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
yesmem-agents 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 10d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Orchestration
Spawn, manage, and communicate with parallel agents via Claude Code or opencode.
Workflow
spawn_agent(project, section)— create agent for a task sectionlist_agents(project)— see all agents and their statusrelay_agent(to, content)— inject message into running agentstop_agent(to)— gracefully stop an agent
spawn_agent Parameters
| Parameter | Purpose | Default |
|---|---|---|
project |
Project name | required |
section |
Task section name | required |
model |
Model override (sonnet, opus, haiku, deepseek-chat, deepseek-v4-pro) | inherited |
max_turns |
Turn limit (0=unlimited) | 0 |
token_budget |
Max tokens (0=config default) | 0 |
caller_session |
Parent session for callbacks | optional |
backend |
"claude", "codex", or "opencode" | "claude" |
Backend choice:
| Backend | Binary | Models | Notes |
|---|---|---|---|
claude |
claude |
sonnet, opus, haiku | Anthropic only. Proxy-integrated prompt cache. Full MCP access. |
codex |
codex |
deepseek-chat, deepseek-v4-pro, GPT models | OpenAI-compatible endpoint. Uses opencode.json provider config. |
opencode |
opencode |
deepseek-chat, deepseek-v4-pro, GPT models | Same as codex but uses opencode binary name. |
Gotchas:
backend: "claude"+model: "deepseek-v4-pro"→ silent failure (0 turns, no output). The claude binary has no DeepSeek endpoint. Always pair DeepSeek models withbackend: "codex"orbackend: "opencode".- Resume is only supported for
backend: "claude".
Communication
| Action | Tool |
|---|---|
| Send to specific agent | relay_agent(to, content) |
| Send to specific session | send_to(target, content) |
| Broadcast to all sessions | broadcast(content, project) |
| Check agent status | get_agent(to) |
| Resume stopped agent | resume_agent(to) |
| Stop all agents | stop_all_agents(project) |
CRITICAL: relay_agent / send_to content MUST end with \n — without trailing newline the prompt stays in the tmux input line and is never submitted. The agent appears unresponsive despite receiving multiple pushes. Always: relay_agent(to, "instruction text\n").
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.
- 10d ago First seen · 58 lines · 43 tokens per session scan A b135f1f1a65c
yesmem-agents is a skill published in the GitHub repository carsteneu/yesmem (41 stars, last pushed 7d ago), licensed Apache-2.0. It adds 43 tokens to every session and 706 once invoked, about $0.0002 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
lithium-kb
Generates, maintains, and visualizes a structured Markdown knowledge base (.lithium-kb/{architecture,debug,tasks,features}) with an interactive Neural Network graph, auto-watch mode, custom agent directives (.agentrules), and MCP server integration for Pi, Claude, Codex, Cursor, and other coding agents. Triggers…
graphifychat
Turn any conversation into a queryable knowledge graph. Three-layer portable memory file: TRON (structured input+output capture with emotion, psychology, intent — every turn), Sparse6 (layered relational graph with community detection, hyperedges, confidence scores — every turn), GRAPHREPORT (god nodes + surprising…
memoryai-core
Primary master orchestrator for MemoryAI autonomous memory. Automatically detects task context, coordinates specialized sub-skills, enforces token budgets, and manages lifecycle.
memoryai
Universal autonomous long-term memory for AI agents. Remember everything, send only what matters.
memoryai-capture
Automatically extracts durable knowledge (decisions, preferences, facts, milestones), executes Memory Brain decisions, and handles temporal conflict invalidation.
memoryai-retrieval
Executes hybrid search (SQLite FTS5 + Dense 384d Vectors), local reranking, and strict token budget context compression.