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 setupgit 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/setup)<a href="https://agentmods.dev/skills/edwin-hao-ai/awareness-sdk/setup"><img src="https://agentmods.dev/badge/skills/edwin-hao-ai/awareness-sdk/setup/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/setup"><img src="https://agentmods.dev/badge/skills/edwin-hao-ai/awareness-sdk/setup.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 | $0.00018 | $0.04036 |
| Opus 5.5 | $0.00007 | $0.01614 |
| Sonnet 5.5 | $0.00004 | $0.00807 |
| Haiku 4.5 | $0.00002 | $0.00404 |
Grade D, and why
setup scanned grade D with 4 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
| `APPROVED:{api_key}` | Success! | Extract the api_key, proceed to Step 3 | Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
mkdir -p ~/.awareness && printf '{"api_key":"%s","api_base":"https://awareness.market/api/v1"}\n' '{api_key}' > ~/.awareness/credentials.json && chmod 600 ~/.awareness/credentials.json Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://localhost:37800/healthz 2>/dev/null && echo "DAEMON:RUNNING" || echo "DAEMON:NOT_RUNNING" Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(['open', url], check=True, capture_output=True) How it starts
The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Awareness Memory: check local daemon status, optionally authenticate via browser, select a memory, and write credentials to settings.json.
Cloud API base URL: https://awareness.market/api/v1 Local daemon URL: http://localhost:37800
Step 1 — Check local daemon
First check if the local Awareness daemon is running:
curl -sf http://localhost:37800/healthz 2>/dev/null && echo "DAEMON:RUNNING" || echo "DAEMON:NOT_RUNNING"
If daemon is running (DAEMON:RUNNING):
Get daemon status:
curl -sf http://localhost:37800/api/v1/status 2>/dev/null || echo "{}"
Tell the user:
Awareness local daemon is running!
Status: [show memory_id, mode, etc. from status response]
MCP URL: http://localhost:37800/mcp
Your local memory is ready to use.
Then ask: "Want to connect to Awareness Cloud for sync and sharing? (yes/no)"
- If no → jump to Step 5 (write local-only settings) and finish.
- If yes → continue to Step 2 (cloud auth).
If daemon is NOT running:
Check if user has existing cloud credentials (same logic as before):
1a. Check environment variables (from settings.json)
Read the current environment variables AWARENESS_API_KEY and AWARENESS_MEMORY_ID.
If both exist AND AWARENESS_API_KEY starts with aw_ AND is NOT the placeholder aw_your-api-key-here,
and AWARENESS_MEMORY_ID is NOT your-memory-id-here:
- Tell the user cloud credentials are already configured.
- Ask: "Do you want to re-configure? (yes/no)"
- If no → stop here. Suggest running
/awareness-memory:session-startinstead. - If yes → continue to Step 2.
1b. Check ~/.awareness/credentials.json (left by npx @awareness-sdk/setup)
Run:
cat ~/.awareness/credentials.json 2>/dev/null
If the file exists and contains a valid api_key (starts with aw_):
- Tell the user: "Found existing Awareness credentials (from a previous setup). Reusing them."
- Extract the
api_keyandapi_basevalues. - Skip Step 2 and Step 3 — jump directly to Step 4 (Memory selection) using this api_key.
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 · 440 lines · 18 tokens per session scan D c887a38d066d
setup is a skill published in the GitHub repository edwin-hao-ai/Awareness-SDK (9 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 4,036 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it D with 4 findings (harvests environment variables, asks for root, 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
ccs-align
Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → getobservations, land them in a seat-owned middle cache via atomic grab → append → filter exclude-marks → replace, manage exclude marks, and walk house → project → seat…
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"…
handoff
Generate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps — so a fresh Claude session can continue exactly where this one left off. Use when sessions are getting long, Claude keeps retrying the same broken solution, or the user wants to step away and resume later.
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.
screenpipe
Search screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.
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?".