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 harnessprotocol/harness-kit --skill memorygit clone --depth 1 https://github.com/harnessprotocol/harness-kitWrote 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/harnessprotocol/harness-kit/memory)<a href="https://agentmods.dev/skills/harnessprotocol/harness-kit/memory"><img src="https://agentmods.dev/badge/skills/harnessprotocol/harness-kit/memory/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/harnessprotocol/harness-kit/memory"><img src="https://agentmods.dev/badge/skills/harnessprotocol/harness-kit/memory.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 | $0.00076 | $0.01519 |
| Opus 5.5 | $0.00030 | $0.00608 |
| Sonnet 5.5 | $0.00015 | $0.00304 |
| Haiku 4.5 | $0.00008 | $0.00152 |
Grade A, and why
memory 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 1mo 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
membrain Memory
Overview
Interface with the membrain knowledge graph — search entities, trace BFS traversals, add observations, create episodes, and check graph health.
Graceful degradation: If membrain MCP tools are not available, print install instructions and exit. If the HTTP server is not running, skip HTTP-dependent subcommands and say so.
Subcommands
Parse the argument after /memory to determine which operation to run.
| Invocation | Operation |
|---|---|
/memory search <topic> |
Search the graph for entities matching the topic |
/memory trace <query> |
Run BFS traversal and display token savings |
/memory add <entity> <observation> |
Add an observation to an existing entity |
/memory episode <text> |
Create a timestamped episode from free text |
/memory status |
Show graph statistics (entity/relation counts) |
/memory (no args) |
Show usage and subcommand list |
Step 1: Check MCP Availability
Before any graph operation, confirm membrain MCP tools are available.
Test: Can you call search_nodes? If the tool is missing from the tool list:
membrain MCP tools are not connected.
To connect them:
1. Install mem: go install github.com/siracusa5/membrain/cmd/mem@latest
2. Add to Claude Code settings (or via /plugin install membrain@harness-kit):
{
"mcpServers": {
"membrain": { "command": "mem", "args": ["mcp"] }
}
}
3. Restart Claude Code
For the desktop UI: mem serve (opens http://localhost:3131)
Step 2: Route to Subcommand
search <topic>
Search the graph for entities and relations related to the topic.
- Call
search_nodeswith the topic as the query - If results < 3, try decomposing the topic into individual keywords and search each (max 2 additional calls)
- Format results:
## Memory: "<topic>"
Found N entities · saved X% tokens vs full graph dump
### <EntityName> (Type)
- observation 1
- observation 2
- observation 3
### <EntityName> (Type)
...
Relations: A → relationType → B
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 202 lines · 76 tokens per session scan A 02f36fc4cef0
memory is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 1,519 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
llm-wiki
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…