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 edwin-hao-ai/Awareness-SDK --skill recallgit 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/recall)<a href="https://agentmods.dev/skills/edwin-hao-ai/awareness-sdk/recall"><img src="https://agentmods.dev/badge/skills/edwin-hao-ai/awareness-sdk/recall/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/edwin-hao-ai/awareness-sdk/recall"><img src="https://agentmods.dev/badge/skills/edwin-hao-ai/awareness-sdk/recall.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00016 | $0.00436 |
| Opus 5 | $0.00008 | $0.00218 |
| Sonnet 5 | $0.00003 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade B, and why
recall 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 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.
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_recall","arguments":{"query":"why did we pick pgvector?","limit 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_recall","arguments":{"query":"why did we pick pgvector?","limit What it actually says
Search Awareness Memory for relevant context.
Query: $ARGUMENTS
How to call Awareness tools
Try MCP tools first (awareness_recall).
If MCP tools are NOT available, use Bash to call the local daemon HTTP API directly:
# F-053: single-parameter — daemon picks scope/mode/detail/weights.
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":"why did we pick pgvector?","limit":10}}}'
The response is JSON-RPC: result.content[0].text contains the tool output as JSON string.
Steps
-
REWRITE the user query into a complete natural-language question with context. Example: "auth bug" → "authentication bug in login flow, JWT token handling, session management"
-
Call
awareness_recallwith ONE parameter:query: the rewritten natural-language question- (optional)
limit: default 6, max 30 - (optional)
token_budget: 5K (default, card-heavy) / 30K (mixed) / 60K+ (raw-heavy)
Daemon auto-routes across memories + knowledge cards + workspace graph and picks the right detail level for your token budget. You do NOT need to choose scope, recall_mode, detail, ids, or weights.
-
Present results clearly:
- Existing implementations that can be reused (include file paths)
- Architectural decisions already made
- Related past work and warnings
Rules:
- Pass ONE query string — daemon handles the rest.
- If results are empty, say so clearly — do not hallucinate.
- Do not dump raw JSON — summarize in plain language.
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 · 47 lines · 16 tokens per session scan B c1d36f2a562f
recall 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 16 tokens to every session and 436 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
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.
claude-mem-install
Use this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai inference.
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.
learn-codebase
Prime a codebase by reading every source file in full. Use when starting work on a new or unfamiliar project, or when the user asks to "learn the codebase", "read the codebase", "prime", or "get up to speed".