agentleFS
Sign inStart free
patrickbdevaneypatrickbdevaney/hermes-max/skills/workflow-codegraph/SKILL.md

workflow-codegraph

Skill1 starsChanged 6 months agoMITView on GitHub

Before editing a function, call code_impact to see its blast radius (what breaks if it changes). Use code_callers/code_callees to understand call flow, code_importers for module dependents, code_dead_code to find unreferenced symbols, and code_structural_search for pattern-based refactoring across files. Trigger before any non-trivial edit to shared/core code, and when planning a refactor.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use code_callees to understand what a function depends on before you trust it.

    line 32
  2. Distinctive:

    Call edges are name-resolved (an over-approximation of dynamic dispatch) — that bias is deliberate for blast radius: better to over-list a …

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

workflow-codegraph

<!-- TRIGGERS WHEN: about to edit a shared/core function, or planning a refactor -->

Deterministic AST code-intelligence (mcp-codegraph) — the STRUCTURAL questions that semantic RAG and per-symbol LSP don't answer. Run index_codegraph(repo_path) once per repo first (fast, no model).

ToolAnswers
code_impact(symbol)blast radius — the transitive set of callers that could break if you change symbol. Call this before editing shared code.
code_callers(symbol) / code_callees(symbol)call hierarchy — who calls it / what it calls
code_importers(file_or_module)which files import this module
code_dead_code()functions/classes never called by name (advisory)
code_structural_search(pattern)ast-grep structural match (e.g. def $F($$$): pass) for pattern-based refactors

Discipline

  • Before changing a function's signature/behavior, run code_impact(name) — the result is the set of call sites you must check. This is how you avoid the "fixed it here, broke it three files away" failure.
  • Use code_callees to understand what a function depends on before you trust it.
  • Complements [[workflow-lsp]] (LSP gives exact, compiler-resolved references for a single symbol; codegraph gives the fast graph-wide blast-radius closure) and search_code (semantic). Reach for codegraph for structural questions.

Call edges are name-resolved (an over-approximation of dynamic dispatch) — that bias is deliberate for blast radius: better to over-list a dependent than miss one.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free