FC subconscious
A bounded, governed self-improvement layer for OpenClaw agents. Consumes learnings from the self-improving-agent skill (produces .learnings/), evolves them through a typed mutation system, and surfaces emerging behavioral patterns as session biases. Triggers on: subconscious system installation, health checks, metabolism management (tick/rotate/review/benchmark), or reviewing what biases are active. Do NOT invoke proactively — only when Edward specifically asks about it or when the system health check cron reports issues.
As a process C 60/100 · Has gaps — weak spots: result and completion, 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 · 15
-
high Dangerous commands
cmd-persistencereferences/INSTALL.md:39Persistence mechanism (cron / launchd / scheduled task / autorun registry)echo "*/5 * * * * cd ~/.openclaw/skills/subconscious/scripts && python3 subconscious_metabolism.py tick >> ~/.openclaw/workspace-alfred/logs/subconscious_tick.log 2>&1" | crontab -
-
high Dangerous commands
cmd-persistencereferences/INSTALL.md:40Persistence mechanism (cron / launchd / scheduled task / autorun registry)echo "0 * * * * cd ~/.openclaw/skills/subconscious/scripts && python3 subconscious_metabolism.py rotate --enable-promotion >> ~/.openclaw/workspace-alfred/logs/subconscious_rotate.log 2>&1" | crontab
-
high Dangerous commands
cmd-persistencereferences/INSTALL.md:41Persistence mechanism (cron / launchd / scheduled task / autorun registry)echo "0 6 * * * cd ~/.openclaw/skills/subconscious/scripts && python3 subconscious_metabolism.py review >> ~/.openclaw/workspace-alfred/logs/subconscious_review.log 2>&1" | crontab -
-
high Dangerous commands
cmd-persistencescripts/install.sh:81Persistence mechanism (cron / launchd / scheduled task / autorun registry)( crontab -l 2>/dev/null | grep -v "subconscious_metabolism.py tick"; \
-
high Dangerous commands
cmd-persistencescripts/install.sh:83Persistence mechanism (cron / launchd / scheduled task / autorun registry)) | crontab -
-
high Dangerous commands
cmd-persistencescripts/install.sh:86Persistence mechanism (cron / launchd / scheduled task / autorun registry)( crontab -l 2>/dev/null | grep -v "subconscious_metabolism.py rotate"; \
-
high Dangerous commands
cmd-persistencescripts/install.sh:88Persistence mechanism (cron / launchd / scheduled task / autorun registry)) | crontab -
-
high Dangerous commands
cmd-persistencescripts/install.sh:91Persistence mechanism (cron / launchd / scheduled task / autorun registry)( crontab -l 2>/dev/null | grep -v "subconscious_metabolism.py review"; \
Medium and low: 7
-
medium Dangerous commands
cmd-persistencereferences/INSTALL.md:65Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)crontab -l | grep -v "subconscious_metabolism" | crontab -
detector -
low Dangerous commands
cmd-cron-mentionreferences/INSTALL.md:65Mentions editing / listing crontabcrontab -l | grep -v "subconscious_metabolism" | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/install.sh:81Mentions editing / listing crontab( crontab -l 2>/dev/null | grep -v "subconscious_metabolism.py tick"; \
-
low Dangerous commands
cmd-cron-mentionscripts/install.sh:86Mentions editing / listing crontab( crontab -l 2>/dev/null | grep -v "subconscious_metabolism.py rotate"; \
-
low Dangerous commands
cmd-cron-mentionscripts/install.sh:91Mentions editing / listing crontab( crontab -l 2>/dev/null | grep -v "subconscious_metabolism.py review"; \
-
low Dangerous commands
cmd-cron-mentionscripts/install.sh:96Mentions editing / listing crontab( crontab -l 2>/dev/null | grep -v "subconscious_benchmark"; \
-
low Dangerous commands
cmd-cron-mentionscripts/install.sh:125Mentions editing / listing crontab (string literal in code, not executed)echo " - To disable auto-promotion: crontab -e and remove --enable-promotion from hourly cron"
code literal
Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: A bounded, governed self-improvement layer for OpenClaw agents. Co… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - note
frontmatter-keyunknown frontmatter key "readme"
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 31 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1645 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
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
- -43 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 527: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (12 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.