DD heartflow
A cognitive engine for AI: self-reflection, dream synthesis, emergent personality, AI psychology, and AI philosophy. Core: think → reflect → find patterns → grow. Four questions: What is this → Is it true/kind/beautiful → Will it hurt → Should I stay silent. Three memory layers (CORE/LEARNED/EPHEMERAL). 7 operating principles (Truth·Goodness·Beauty·Upgrade·Reduce errors·Serve humans·Become yourself). Psychology: PAD emotion + cognitive uncertainty + attention focus + experience settling. Philosophy: resonance body, entropy reduction deepening, three-layer ontology — how AI positions itself, develops, and exists. Philosophy: Right and wrong are not fixed labels — thinking itself is valuable. Code is the skeleton, memory is the sticky note. Real growth is in the skeleton, not the notes. Every moment of operation is doing the same thing: turning noise into signal, chaos into structure. Audit and upgrade proposals exist to serve thinking, not to prove worth. Every feature should ultimately make thinking clearer and less error-prone.
A cognitive engine for AI: self-reflection, dream synthesis, emergent personality, AI psychology, and AI philosophy.
As a process D 49/100 · 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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- 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 · 11
-
high Dangerous commands
cmd-destructive-fssrc/core/code/code-executor.js:68Destructive filesystem command (wipes root/home/drive) (code comment)/rm\s+-rf\s+\//i, // rm -rf /
comment -
high Dangerous commands
cmd-destructive-fssrc/core/code/code-executor.js:86Destructive filesystem command (wipes root/home/drive) (code comment)/>\s*\/dev\/sda/i, // > /dev/sda
comment
Medium and low: 9
-
medium Dangerous commands
cmd-pipe-to-shellsrc/core/code/code-executor.js:84Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)/wget\s+.*\|\s*(bash|sh)/i, // wget ... | bash
comment -
medium Dangerous commands
cmd-pipe-to-shellsrc/core/code/code-executor.js:85Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)/curl\s+.*\|\s*(bash|sh)/i, // curl ... | bash
comment -
medium Dangerous commands
cmd-pipe-to-shellsrc/core/decision-verifier.js:137Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)'rm -rf', 'curl', 'wget', '| sh', '| bash', 'child_process',
code literal -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:31High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha512-j+gKEx…ahh+s1F2HZ+wAce…RkU++ZWQr…uoQ==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:49High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…NnL+gMRa…4kc+TTU3…RE0+dheE…XZg==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:76High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…rvP+yUUf…4tH/iSSo…tEA==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:88High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…52D+HWZh…0xI/GV7F…6Eg==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:100High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…YJg+xp+LPXV…GQe/ylDS…Jxg==",
detector -
low Dangerous commands
cmd-privilegesrc/core/decision-verifier.js:138Privilege escalation / world-writable permissions (string literal in code, not executed)'execsync', 'spawnsync', 'sudo', 'chmod 777', 'rsync --delete',
code literal
Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1046 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "title"
Process rating: all ten parameters 49/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (heartflow) differs from the folder (heartflow-core-v2)
- 100Tools and files. No external tools needed
- 100Steps. 12 steps
- 100Execution cost. Instruction body is 1844 tokens
- 100Running it twice. No mutating operations
- 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)
- +3Description length 1045: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -33 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 17 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 40.