SKILLEMALL.ai

AD deep-recall

Recursive memory recall for persistent AI agents using RLM (Recursive Language Models). Implements the Anamnesis Architecture — "The soul stays small, the mind scales forever."

modbender/skill-library-mcp Agent Skills author: modbender MIT 8 files body ≈ 741 tokens Open the sourcegithub.com analyzed 2 d ago

Recursive memory recall for persistent AI agents using RLM (Recursive Language Models).

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, failures and branches

ProcedureGitHubAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
94
Quality 40%
84
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Failures and branches w 10
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

    For the model run — optional
    • 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
    • medium Exfiltration net-redirectable-api-key rlm_config_builder.py:82
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • low Dangerous commands cmd-pipe-to-shell-known-host deep_recall.py:166
      Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
      "  curl -fsSL https://deno.land/install.sh | sh"
      code literal

    Files scanned: 8. 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 46/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 1 mutating operations with no state check
    • 40Consistency. Frontmatter name (deep-recall) differs from the folder (deeprecall)
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 22 steps, 1 vague phrases
    • 100Execution cost. Instruction body is 741 tokens
    • 100Progress reporting. Reports progress
    • 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
    • +1No license
    • +2Single-language instructions
    • +3Description length 176: enough signal without eating the budget
    • +4Structure: 12 headings
    • +3Step-by-step instructions: 22 items
    • +4Has examples (1 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.