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/edwin-hao-ai/awareness-sdk/session-startnpx skills add edwin-hao-ai/Awareness-SDK --skill session-startgit clone --depth 1 https://github.com/edwin-hao-ai/Awareness-SDKWrote 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/edwin-hao-ai/awareness-sdk/session-start)<a href="https://agentmods.dev/skills/edwin-hao-ai/awareness-sdk/session-start"><img src="https://agentmods.dev/badge/skills/edwin-hao-ai/awareness-sdk/session-start.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 5.1 | $0.00019 | $0.01002 |
| Opus 5 | $0.00010 | $0.00501 |
| Sonnet 5 | $0.00004 | $0.00200 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade B, and why
session-start scanned grade B with 2 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 6d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST http://localhost:37800/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"awareness_init","arguments":{"source":"claude-code"}}}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://localhost:37800/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"awareness_init","arguments":{"source":"claude-code"}}}' How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize Awareness Memory session and load project context.
How to call Awareness tools
Try MCP tools first (awareness_init, awareness_recall, awareness_record, awareness_lookup).
If MCP tools are NOT available, use Bash to call the local daemon HTTP API directly:
# awareness_init — fresh session, no prior-session noise (default max_sessions=0)
curl -s -X POST http://localhost:37800/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"awareness_init","arguments":{"source":"claude-code"}}}'
# awareness_init — resume/continuity mode, include last N session summaries
curl -s -X POST http://localhost:37800/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"awareness_init","arguments":{"source":"claude-code","max_sessions":3}}}'
# awareness_recall — pass ONE query string, daemon picks the rest
curl -s -X POST http://localhost:37800/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"awareness_recall","arguments":{"query":"<natural-language question>","limit":10}}}'
# awareness_record — pass ONE content string (action=remember is implied)
curl -s -X POST http://localhost:37800/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"awareness_record","arguments":{"content":"<detailed description>","insights":{"knowledge_cards":[...],"action_items":[...],"risks":[...]}}}}'
The response is JSON-RPC: result.content[0].text contains the tool output as JSON string.
Steps
- Call
awareness_initwith source: "claude-code".- Default mode (fresh session):
awareness_init({ source: "claude-code" })— no prior-session summaries in payload, saves ~500-1000 prompt tokens for brand-new tasks. - Resume mode:
awareness_init({ source: "claude-code", max_sessions: 3 })— adds last 3 session summaries for explicit continuity ("continue where we left off"). - Heuristic: if $ARGUMENTS mentions "continue / resume / yesterday / last time", use resume mode.
- Default mode (fresh session):
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.
- 6d ago First seen · 70 lines · 19 tokens per session scan B 95381b457545
session-start is a skill published in the GitHub repository edwin-hao-ai/Awareness-SDK (9 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,002 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
memory-protocol
Universal protocol for total-agent-memory MCP server. Activate at session start, before any non-trivial task, after every significant action, on errors, and at session end. Relevant whenever the user mentions: memory, recall, past context, decisions history, conventions, lessons learned, "продолжаем", "сохранись"…
memory
Activate this skill when starting a new session, beginning a new task, saving knowledge, recalling past decisions, or after completing significant work. Also activate on errors to log them for pattern analysis. Relevant when the user asks about memory, past context, lessons learned, decisions history, project…
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
how-it-works
Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".
openclaw
This guide walks through setting up the claude-mem plugin on an OpenClaw gateway. By the end, your agents will have persistent memory across sessions via system prompt context injection, and optionally a real-time observation feed streaming to a messaging channel.