ln-022-researchgraph — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ln-022-researchgraph (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.
Paths: File paths are relative to this skill directory.
Type: Standalone Utility Category: 0XX Dev Environment
Indexes and queries canonical project research files through hex-research-mcp: hypotheses, goals, tasks, sources, source library entries, benchmark run manifests, evidence links, derived goal metrics, lineage, generated research maps, and audit gaps.
MANDATORY READ: Load references/researchgraph_mcp_usage.md
| Input | Required | Source | Description |
|---|---|---|---|
project_path | yes | args or CWD | Project root containing research graph files |
command | no | args | Specific action: audit, inspect H##, goal G##, runs, evidence, lineage, progress, proposed, canvas |
Use this skill when the project has any of:
docs/hypotheses/*.mddocs/goals/*.mdbenchmark/runs/*/manifest.yamlUse it when the user asks about research status, live or pending hypotheses, goal readiness, benchmark evidence, source quality, evidence depth, proposal readiness, implementation gaps, drift, field-level changes, or a visual/generated research map.
Do not use this skill for code symbol ownership, call graphs, references, or edit blast radius. Use ln-021-codegraph or host hex-graph policy for semantic code questions.
Use hex-research when available. If unavailable, manually read the split research files with Glob/Grep/Read, answer from direct file evidence, and mark confidence as degraded.
Treat STALE as actionable graph debt or missing project metadata, not as a tool failure. Treat INVALID from verify_index as diagnostic unless a write/index operation fails.
Check for the canonical layout:
docs/hypotheses/*.mddocs/goals/*.mdbenchmark/runs/*/manifest.yamlIf none exist, stop and report that the project does not expose a research graph yet. Do not invent hypotheses or goals.
Start read-only:
verify_index({ path: "{project_path}" })Rebuild only when the index is missing, stale, explicitly requested, or the task requires current graph state:
index_hypotheses({ path: "{project_path}" })The local index is stored under .hex-skills/researchgraph/ in the target project.
| User intent | Tool |
|---|---|
| live, pending, rejected, mixed, not-started hypotheses | find_hypotheses |
inspect H## | inspect_hypothesis |
inspect G## or goal status | inspect_goal |
| evidence, sources, benchmark proof | find_evidence |
| targeted or comprehensive benchmark runs | find_runs |
| parent/child hypothesis chain | trace_lineage |
| graph hubs, disconnected nodes, shape | analyze_topology |
| missing goals, sources, task gaps, drift | audit_orphans |
| goal tree | trace_goal_tree |
| goal readiness, derived metrics, and metric coverage | inspect_goal, audit_goal_alignment |
| source quality or evidence depth | inspect_hypothesis, find_evidence, analyze_proposed |
| changed research files and field-level deltas in current diff | analyze_progress |
| readiness of proposed next hypotheses | analyze_proposed |
| JSON Canvas export | export_canvas |
generated docs/research-map.md export | export_research_map |
Report:
OK, STALE, INVALID, ERROR)For export_canvas and export_research_map, run dry-run first. Write only after dry-run output is useful and the user requested the file. Treat split files as canonical; generated research-map.md is not a second manual source of truth.
When MCP is unavailable:
docs/goals/*.md and docs/hypotheses/*.md frontmatter first.benchmark/runs/*/manifest.yaml only after narrowing by H/G IDs or status.H04, G1) over broad scans.STALE / graph debt separated from MCP/tool failureVersion: 0.1.0 Last Updated: 2026-05-08
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.