Local-first engineering memory for AI coding: a git-native graph of decisions, bugs, and invariants, exposed to Claude Code via MCP.
- capability exposure inferred + 35
- tool safety inferred + 12
- trust mitigators mixed − 17
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 6m ago · see ecosystem CVEs →
- C · 38 → B · 30
- C · 53 → C · 38
- C · 41 → C · 53
No known CVEs for this server.
- high dangerous code
obfuscated payload: dynamic require()/import()
- low dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
analyzed v1.8.3 · analyzer v33 · 1w ago
skills & prompt files 18
- skill davesheffer-hunch-92bb6cc/.agents/skills/fable-mode/SKILL.md
- skill davesheffer-hunch-92bb6cc/.agents/skills/source-command-hunch-fragile/SKILL.md
- agent-rules davesheffer-hunch-92bb6cc/.claude/commands/capture.md
- agent-rules davesheffer-hunch-92bb6cc/.claude/commands/heal.md
- agent-rules davesheffer-hunch-92bb6cc/.claude/commands/hunch-fix.md
- agent-rules davesheffer-hunch-92bb6cc/.claude/commands/hunch-fragile.md
- agent-rules davesheffer-hunch-92bb6cc/.claude/commands/hunch-why.md
- skill davesheffer-hunch-92bb6cc/.claude/skills/fable-mode/SKILL.md
- agent-rules davesheffer-hunch-92bb6cc/.cursor/rules/hunch.mdc
- agent-rules davesheffer-hunch-92bb6cc/.github/copilot-instructions.md
- agent-rules davesheffer-hunch-92bb6cc/.windsurf/rules/hunch.md
- agent-rules davesheffer-hunch-92bb6cc/AGENTS.md
- agent-rules davesheffer-hunch-92bb6cc/CLAUDE.md
- skill davesheffer-hunch-92bb6cc/plugin/skills/capture/SKILL.md
- skill davesheffer-hunch-92bb6cc/plugin/skills/fix/SKILL.md
- skill davesheffer-hunch-92bb6cc/plugin/skills/fragile/SKILL.md
- skill davesheffer-hunch-92bb6cc/plugin/skills/heal/SKILL.md
- skill davesheffer-hunch-92bb6cc/plugin/skills/why/SKILL.md
Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of davesheffer.