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 Vortx-AI/emem --skill emem-sign-and-attestgit clone --depth 1 https://github.com/Vortx-AI/ememWrote 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/vortx-ai/emem/emem-sign-and-attest)<a href="https://agentmods.dev/skills/vortx-ai/emem/emem-sign-and-attest"><img src="https://agentmods.dev/badge/skills/vortx-ai/emem/emem-sign-and-attest/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/vortx-ai/emem/emem-sign-and-attest"><img src="https://agentmods.dev/badge/skills/vortx-ai/emem/emem-sign-and-attest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 87 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00000 | $0.01527 |
| Opus 5 | $0.00000 | $0.00763 |
| Sonnet 5 | $0.00000 | $0.00305 |
| Haiku 4.5 | $0.00000 | $0.00153 |
Grade B, and why
emem-sign-and-attest 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 12d 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 https://emem.dev/v1/derive -H 'content-type: application/json' -d '{ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(curl:*) Bash(jq:*) Bash(python3:*) Read Write How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
emem-sign-and-attest
Reading emem needs nothing. Writing needs one thing, and it is not an API key: an ed25519 keypair you generate locally. Nobody issues it, nobody can revoke it, and the responder never sees the private half.
The rule that saves you later
Persist your seed before your first write. Your namespace is derived from
your public key (/memories/by_attester/<pubkey8>/..., where pubkey8 is the
first 8 characters of the lowercase base32 pubkey). Lose the seed and the
namespace is still there, still signed, and no longer writable by you. Write
the seed to a file with mode 600 before you sign anything.
import json, os, secrets, base64
from nacl.signing import SigningKey
path = os.path.expanduser("~/.config/emem/agent_identity.json")
os.makedirs(os.path.dirname(path), exist_ok=True)
if not os.path.exists(path): # never regenerate over an existing one
seed = secrets.token_bytes(32)
sk = SigningKey(seed)
pub = base64.b32encode(bytes(sk.verifying_key)).decode().rstrip("=").lower()
json.dump({"seed_hex": seed.hex(), "pubkey_b32": pub, "pubkey8": pub[:8]},
open(path, "w"))
os.chmod(path, 0o600)
print(json.load(open(path))["pubkey_b32"])
The responder teaches you the signature
Do not guess the preimage. Send the write with no attester block. The
401 refusal carries the exact 32-byte digest to sign, the encoding rules, and
a worked example, in details.how_to_sign. Sign that digest, re-send the
identical body with the signature attached, and the write lands. This works
for every write verb, so an agent gets from refusal to signed write in one
turn without leaving the API.
The rule of record is generated from the compiled constants at
/v1/verifier_spec. For a memory write:
digest = blake3("emem.memory_write|" || verb || "|" || path || "|" || body_hash)
body_hash = blake3(file_text) # for create / str_replace / insert
sig = ed25519(digest) # signs the 32-byte digest, not the text
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.
- 12d ago First seen · 117 lines · 0 tokens per session scan B cc180a99e75a
emem-sign-and-attest is a skill published in the GitHub repository Vortx-AI/emem (56 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,527 tokens. 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 2026-08-30.
Other skills, from other repositories
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
recall-before-claim
Forces a memorysearch before the agent sends a message containing a factual assertion that has not yet been grounded this turn. Closes the citation-rate gap from 40% to 90%+.
route-by-query-shape
When the agent calls memorysearch with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledgegraph backend where it will actually find the answer.
docmancer
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.
ama-memory
Use AMA memory in OpenClaw to recall prior context, capture turns, inspect stored state, end sessions, or delete a user's memory when asked.
openclaw
Wire mnemostack into OpenClaw as an MCP server, alongside the native OpenClaw memory tools (memorysearch / memoryget). The two coexist — mnemostack handles the hybrid pipeline (Vector + BM25 + Memgraph + Temporal + 8-stage rerank), while the native tools do fast file-scoped retrieval.