AC agentmemo
agentMemo is a Semantic Memory Mesh server for AI agents. Use this skill when you need to store, search, or retrieve agent memory across sessions with semantic understanding. Triggers when: (1) an agent needs persistent memory between conversations, (2) multi-agent systems need shared namespaces with RBAC isolation, (3) hybrid semantic+keyword search over stored context is required, (4) versioned memory with rollback is needed, (5) real-time event streaming (SSE/WebSocket) between agents is desired, or (6) batch memory operations are needed. Built on FastAPI + SQLite + HNSW (384-dim all-MiniLM-L6-v2 embeddings). Requires python3/pip, AGENTMEMO_ADMIN_KEY env var, and pip install -r requirements.txt. First run downloads ~90MB model from HuggingFace.
As a process C 57/100 · Has gaps — weak spots: result and completion, consistency, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
read-dotenvinstall.sh:63Reads a .env file (detector / deny-list definition)echo " env \$(cat .env | xargs) .venv/bin/python server.py"
detector -
low Exfiltration
read-dotenvscripts/install.sh:63Reads a .env file (detector / deny-list definition)echo " env \$(cat .env | xargs) .venv/bin/python server.py"
detector
Files scanned: 26. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (agentmemo) differs from the folder (agentmemo-karl)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 13 steps
- 100Execution cost. Instruction body is 1075 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 757: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.