rpg — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited rpg (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Whenever the user asks about code structure, behavior, relationships, impact, dependencies, or cross-file patterns, reach for RPG commands BEFORE falling back to grep, cat, find, wc, or Read. RPG is indexed, semantically organized, and answers structural questions in one call that would otherwise require dozens of chained text searches.
| If you'd otherwise... | Use this instead |
|---|---|
grep -r by intent | rpg-encoder search "describe what it does" |
grep -r by name | rpg-encoder search "name" --mode snippets |
cat file for a function | rpg-encoder fetch "file:func" |
| chained greps for callers | rpg-encoder explore ENTITY --direction up |
| chained greps for callees | rpg-encoder explore ENTITY --direction down |
wc -l / find / tree | rpg-encoder info |
| reading many files | Use the MCP semantic_snapshot tool if available |
Fall back to grep / cat / Read only when the query is about literal text (string search, comments, TODOs, log messages) — not structure or semantics.
If you have the RPG MCP server connected, prefer its tools (search_node, fetch_node, explore_rpg, impact_radius, plan_change, semantic_snapshot, context_pack) over the CLI — they're faster and return structured data.
You have access to rpg-encoder, a CLI tool that builds semantic code graphs (Repository Planning Graphs) from any codebase. Use it to understand code structure, search by intent, trace dependencies, and perform autonomous semantic lifting.
rpg-encoder buildDetects languages automatically, parses all source files, builds structural hierarchy and dependency edges. Creates .rpg/graph.json. Use --force to rebuild.
rpg-encoder search "validate user input"
rpg-encoder search "database connection" --mode features
rpg-encoder search "auth" --mode snippets
rpg-encoder search "parse config" --scope DataProcessingModes: auto (default, tries both), features (semantic intent), snippets (name/path matching).
rpg-encoder fetch "src/auth.rs:validate_token"Returns entity type, file location, semantic features, source code, and dependency edges (invokes/invoked-by).
rpg-encoder explore "src/auth.rs:validate_token" --direction both --depth 3Directions: up (what calls it), down (what it calls), both.
rpg-encoder infoShows entity count, file count, lifting coverage, hierarchy, functional areas, edge counts.
# Estimate cost first
rpg-encoder lift --dry-run
# Lift with Anthropic Haiku (default, cheapest)
rpg-encoder lift --provider anthropic
# Lift with OpenAI GPT-4o-mini
rpg-encoder lift --provider openai --model gpt-4o-mini
# Lift specific scope
rpg-encoder lift --scope "src/auth/**"Performs full autonomous lifting: auto-lift trivial entities, LLM-lift the rest, synthesize file features, discover domains, and assign hierarchy. Saves after each batch for crash recovery.
API key: pass --api-key KEY or set ANTHROPIC_API_KEY / OPENAI_API_KEY env var.
rpg-encoder update
rpg-encoder diff # dry-run: see what would changerpg-encoder export --format dot # Graphviz DOT
rpg-encoder export --format mermaid # Mermaid flowchartrpg-encoder validaterpg-encoder hook install
rpg-encoder hook uninstallrpg-encoder build to indexrpg-encoder info to see structurerpg-encoder search "main entry point" to find key entitiesrpg-encoder explore ENTITY --direction down to trace call chainsUse --mode features with natural language describing behavior:
rpg-encoder search "handle authentication" --mode features
rpg-encoder search "serialize data to JSON" --mode featuresrpg-encoder search "function_name"rpg-encoder explore ENTITY --direction up --depth 3rpg-encoder build (if not done)rpg-encoder lift --dry-run (check cost)rpg-encoder lift (run lifting)rpg-encoder info (verify coverage)-p /path/to/project to target a different directory..rpg/graph.json — add .rpg/ to .gitignore or commit it for team sharing.rpg-encoder lift continues from where it stopped.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.