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-remembergit 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-remember)<a href="https://agentmods.dev/skills/carsteneu/yesmem/yesmem-remember"><img src="https://agentmods.dev/badge/skills/carsteneu/yesmem/yesmem-remember/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-remember"><img src="https://agentmods.dev/badge/skills/carsteneu/yesmem/yesmem-remember.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 | $0.00070 | $0.00507 |
| Opus 5 | $0.00035 | $0.00253 |
| Sonnet 5 | $0.00014 | $0.00101 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade A, and why
yesmem-remember 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 9d 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.
What it actually says
Saving Knowledge
Store learnings with structured metadata for better retrieval.
Workflow
- Identify what to save (decision, gotcha, pattern, preference, teaching)
- Call
remember()with rich metadata - For completed tasks:
resolve_by_text(text)orresolve(learning_id, reason) - For connected insights:
relate_learnings(id_a, id_b, relation_type)
remember() Parameters
| Parameter | Purpose | Example |
|---|---|---|
text |
What to remember | "CGO is disabled in yesmem Makefile" |
category |
gotcha, decision, pattern, preference, explicit_teaching, strategic | "decision" |
entities |
Files, systems, people | ["Makefile", "CGO"] |
actions |
Commands, operations | ["go build", "make deploy"] |
trigger |
When to surface this | "When discussing CGO or cross-compilation" |
context |
Why this matters | "Breaks tree-sitter integration" |
anticipated_queries |
3-5 search phrases | ["CGO disabled", "cross compile yesmem"] |
source |
user_stated, agreed_upon, claude_suggested | "agreed_upon" |
project |
Project scope | "yesmem" |
supersedes |
ID of learning this replaces | 12345 |
relate_learnings()
Connect two learnings with semantic edges:
supports— one learning confirms anothercontradicts— learnings conflictdepends_on— one requires the otherrelates_to— general connection
Tips
anticipated_queries: vary between short keywords and full questionssourcetrust hierarchy: user_stated > agreed_upon > claude_suggested- Use
supersedeswhen updating outdated knowledge — don't create duplicates resolve_by_textfinds matching open tasks by text search
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.
- 9d ago First seen · 44 lines · 70 tokens per session scan A 4338bdb32221
yesmem-remember is a skill published in the GitHub repository carsteneu/yesmem (41 stars, last pushed 6d ago), licensed Apache-2.0. It adds 70 tokens to every session and 507 once invoked, about $0.0003 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
honcho-cli
Inspect and debug Honcho workspaces via the honcho CLI. Use when investigating peer representations, memory state, session context, or dialectic quality — any task that requires introspection of a Honcho deployment, including verifying that a recall/record memory loop is actually working.
save-bugfix
After resolving any bug, save what broke, the root cause, and the fix as a CogmemAi memory so the same problem never has to be debugged twice. Use immediately after a bug is fixed, after diagnosing a flaky test, after recovering from a production incident, or after the user says "got it working", "that fixed it"…
search-before-debugging
Before debugging any new bug, error, or unexpected behavior, search CogmemAi for an existing fix from this or any prior session. Use the moment a bug, error message, stack trace, failed test, or unexpected behavior appears, BEFORE running diagnostic commands or reading code. Eliminates duplicate debugging across the…
troubleshooting
Diagnoses and repairs core-memory-kit itself when the memory system is broken — the per-failure-code repair book. Fire whenever a "⚠ [core-memory-kit]" whisper appears on the prompt (it names the failure and points here), or when the user reports a kit symptom however they phrase it: memory is not being saved, nothing…
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…
memory-doctor
Run Locus environment health check — 10-point diagnostic covering Node.js version, storage backend, FTS5, DB permissions, git availability, and more. Use when troubleshooting plugin issues or checking setup.