CD agentic-os
Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.
Promises a multi-agent OS architecture with kernel, specialists, slash commands, file-based memory, and scheduler—all on Claude Code without external databases. Single file with 2974 tokens, no scripts included.
Audit found a dangerous command in the code. Quality score 84, but process score only 43—description exists, implementation is rough. Safety 82: not critical, but flagged. Never tested on actual models.
Don't install. One file can't deliver a full OS, the dangerous command needs rewriting, and zero test runs mean it's untested in practice.
Build persistent multi-agent operating systems on Claude Code.
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 1
-
high Dangerous commands
cmd-persistenceSKILL.md:219Persistence mechanism (cron / launchd / scheduled task / autorun registry)<!-- ~/Library/LaunchAgents/com.agentic.daily-sync.plist -->
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 311, 318): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 85Steps. 15 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2974 tokens
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 tags): a typed call is more reliable
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 327: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (19 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.