Skip to main content

hindsight-architect

Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code.

Install this skill

or
91/100

Security score

The hindsight-architect skill was audited on Aug 19, 2026 and we found 5 security issues across 3 threat categories. Review the findings below before installing.

Categories Tested

Security Issues

low line 17

Command substitution pattern

SourceSKILL.md
15# Hindsight skill preamble - detect environment and existing config
16_HS_VERSION="0.1.0"
17_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
18_PROJECT=$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || basename "$(pwd)")
19
low line 18

Command substitution pattern

SourceSKILL.md
16_HS_VERSION="0.1.0"
17_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
18_PROJECT=$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || basename "$(pwd)")
19
20# Detect existing Hindsight configuration
low line 46

Access to home directory dotfiles

SourceSKILL.md
44
45# 2. Global CLI config (less specific than project)
46if [ "$_DEPLOY_MODE" = "unknown" ] && [ -f ~/.hindsight/config ]; then
47 _HS_CONFIGURED="yes"
48 if grep -q "api.hindsight.vectorize.io" ~/.hindsight/config 2>/dev/null; then
low line 48

Access to home directory dotfiles

SourceSKILL.md
46if [ "$_DEPLOY_MODE" = "unknown" ] && [ -f ~/.hindsight/config ]; then
47 _HS_CONFIGURED="yes"
48 if grep -q "api.hindsight.vectorize.io" ~/.hindsight/config 2>/dev/null; then
49 _DEPLOY_MODE="cloud"
50 else
medium line 281

False safety assurance

SourceSKILL.md
279- Hindsight analyzes the memories to find relevant ones — you don't need to pre-classify them
280
281**Tags use AND matching.** Only memories with ALL specified tags are included. This is fine because tags are identity scopes that naturally co-occur.
282
283**Mental model retrieval:** Fetching a mental model is a fast, direct lookup — not an expensive operation. Use `get_mental_model(bank_id, mental_model_id)` to fetch by ID, or `list_mental_models(bank_id)` to list all models in a bank. The application stores or derives the mental model ID and fetches the content directly. This is a key-value lookup, not a search — use it freely before every response when you need the model's content.
Scanned on Aug 19, 2026
View Security Dashboard
Installation guide →
GitHub Stars 20.2K
Rate this skill
Categorydevelopment
UpdatedSeptember 28, 2026
vectorize-io/hindsight