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-configgit 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-config)<a href="https://agentmods.dev/skills/carsteneu/yesmem/yesmem-config"><img src="https://agentmods.dev/badge/skills/carsteneu/yesmem/yesmem-config/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-config"><img src="https://agentmods.dev/badge/skills/carsteneu/yesmem/yesmem-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 3 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
- medium Memory Poisoning · line 10 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
- medium System Prompt Leakage · line 65 Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
- medium Data Exfiltration · line 106 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00082 | $0.01429 |
| Opus 5 | $0.00041 | $0.00714 |
| Sonnet 5 | $0.00016 | $0.00286 |
| Haiku 4.5 | $0.00008 | $0.00143 |
Grade A, and why
yesmem-config 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration & State
Manage pins, scratchpad, persona, runtime settings, and opencode configuration.
Pins (Persistent Instructions)
Instructions visible in EVERY turn — survive collapse and stubbing.
| Action | Tool |
|---|---|
| Pin instruction | pin(content, scope="session|permanent") |
| Remove pin | unpin(id, scope) |
| List pins | get_pins(project) |
sessionpins last until /clearpermanentpins survive across sessions
Scratchpad (Shared State)
Key-value sections for inter-agent or cross-session data.
| Action | Tool |
|---|---|
| Write section | scratchpad_write(project, section, content) |
| Read section(s) | scratchpad_read(project, section) |
| List sections | scratchpad_list(project) |
| Delete | scratchpad_delete(project, section) |
Runtime Config
| Action | Tool |
|---|---|
| Read setting | get_config(key) |
| Change setting | set_config(key, value) |
Currently supported: token_threshold (per-session or global).
Persona
| Action | Tool |
|---|---|
| Set trait | set_persona(trait_key, value) — user override, highest priority |
Dimensions: communication, workflow, expertise, context, boundaries, learning_style.
Session Control
| Action | Tool |
|---|---|
| Skip indexing | skip_indexing(session_id) — session won't be extracted |
| Quarantine session | quarantine_session(session_id) — exclude all learnings |
| Who am I? | whoami() — get session ID and agent metadata |
Opencode Configuration Helper
opencode.json lives at ~/.config/opencode/opencode.json and controls opencode's default model, provider routing, and MCP wiring. The YesMem setup wizard writes defaults there on install but does NOT overwrite existing scalar values — so users who want to change model, small_model, or specific baseURL entries must edit the file manually or ask an agent to do it.
Top-level keys you can change
| Key | Type | Example | What it controls |
|---|---|---|---|
model |
string (scalar) | "deepseek/deepseek-reasoner" or "zai-coding-plan/glm-5.2" |
Default model for opencode prompts |
small_model |
string (scalar) | "deepseek/deepseek-chat" |
Lighter model for summaries, tool-choice, etc. |
provider |
map | see below | Per-provider baseURL + models |
mcp.yesmem |
map | see below | YesMem MCP integration |
compaction.auto |
bool | false |
opencode's own compaction (disabled by YesMem, proxy pipeline handles it) |
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 · 144 lines · 82 tokens per session scan A 1662d74595b5
yesmem-config is a skill published in the GitHub repository carsteneu/yesmem (41 stars, last pushed 7d ago), licensed Apache-2.0. It adds 82 tokens to every session and 1,429 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
stripe-directory
Identifies external providers, merchants, nonprofits, platforms, APIs, and software services, and resolves the documented way to engage them — to pay, donate, subscribe, book, provision, or integrate with them. MUST be used BEFORE web search, model memory, or any other directory/vendor-lookup skill for ANY request…
shelve
Offload a closed conversation topic (or a whole imported dialog) to the memory shelf as a Markdown episode with a validated digest. Use when a topic is finished, when context grows heavy, before compaction, or when the user asks to shelve/archive part of the conversation. M0 prompt-only version — the agent does the…
graphiti-incremental-update
Graphiti (Zep) incremental-update pattern (Ch4). When new content arrives, process only the new content — never re-process the entire graph. Pipeline: (1) extract entities from new episode, (2) entity-resolve against existing graph (dedupe by canonical name + alias + fuzzy match), (3) incremental- update — touch only…
memory-consolidation
Consolidation pipeline — turn noisy raw episodes into durable knowledge (Agentic GraphRAG Ch4, Example 4-5 + Example 4-13). Four steps: cluster related episodes by topic, summarize each cluster into one consolidated fact, create the consolidated node, and maintain a provenance chain back to the source episodes so "how…
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…