Openmind code graphs
Skill HelloThisWorld/agent-skill-verification-template/skills/openmind-code-graphs
Production-oriented template for building AI agent skills as verifiable software components — offline eval harness, source-grounding validators, structured logs/traces/metrics, replay artifacts, and a CI quality gate. Runs fully offline with a deterministic mock model.
npx -y skills add HelloThisWorld/agent-skill-verification-template --skill openmind-code-graphsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Answer code-structure questions (definition sites, usage sites) from Open Mind's deterministic structure map — real defs, imports and call sites recovered from the corpus code, never invented nodes or edges. Runs Open Mind's real Python implementation through the skill bridge.
SKILL.md
1.2 KB, as published. Nobody here has run it
openmind-code-graphs
This skill is the eval-harness face of Open Mind's code-graphs capability
(https://github.com/HelloThisWorld/open-mind, skills/code-graphs/SKILL.md).
Answers come from Open Mind's actual structure analysis
(openmind/structure.py: build_structure, get_definition, term_usage),
reached through openmind/skill_bridge.py.
Behavior under contract
- Recovered, never generated — definition sites and usage edges come from line-oriented static analysis of the corpus's real code.
- Source locations everywhere — a definition claim cites the actual
file:lineof thedef/classstatement, re-verified on every run. - Honest absence — a symbol not defined in the corpus returns
insufficient_evidencewith zero claims; usage lists only files that truly reference the symbol.
Question forms
where is <symbol> defined · who uses <symbol>