axon-code-intel
Skill4 starsChanged 3 months agoMITView on GitHub
When and how to use Axon code-intelligence tools (call graphs, impact analysis, dead-code detection, execution-flow tracing) during exploration, implementation, and review. Apply when reasoning about structural impact or navigating an unfamiliar codebase; requires Axon installed.
In this repository53 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- actionableSkill
- astro-bootstrapSkill
- astro-patternsSkill
- autopilotSkill
- brainstormingSkill
- commit-conventionsSkill
- cross-repo-contextSkill
- django-bootstrapSkill
- django-patternsSkill
- executeSkill
- find-sessionSkill
- flutter-bootstrapSkill
- flutter-patternsSkill
- full-featureSkill
- intelSkill
- nextjs-bootstrapSkill
- nextjs-fullstack-bootstrapSkill
- nextjs-fullstack-patternsSkill
- nextjs-mui-bootstrapSkill
- nextjs-patternsSkill
- nextjs-shadcn-bootstrapSkill
- orchestratorSkill
- phase-breakdownSkill
- plan-and-scopeSkill
- prdSkill
- reactSkill
- recallSkill
- reflectSkill
- relaySkill
- rememberSkill
- scaffoldSkill
- scratchSkill
- tailwindSkill
- ux-specSkill
- ux-to-promptsSkill
- verify-astroSkill
- verify-djangoSkill
- verify-flutterSkill
- verify-nextjs-fullstackSkill
- verify-nextjs-muiSkill
- verify-nextjs-shadcnSkill
- verify-nextjsSkill
- verifySkill
- visual-feedbackSkill
- work-disciplineSkill
- worktreesSkill
- wrapSkill
- write-as-friendSkill
- write-as-humanSkill
- writing-clearlySkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 36
Use impact results to identify tests and call sites that need updating alongside your change
- Very specific: line 50
If the MCP server runs with axon serve --watch, the index stays current automatically (file-local phases update immediately, global phases …
- Distinctive: line 58
Before relying on Axon tools, verify the index exists:
- Very specific: line 59
Run axon_list_repos to check if the current repo is indexed
- Very specific: line 60
If not indexed, inform the user and suggest running axon analyze .
≈ “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.
Files
Skill: Axon Code Intelligence
Purpose
Guide the use of Axon's MCP tools for structural code analysis during planning, execution, and verification.
What Axon Provides
Axon indexes codebases into a knowledge graph — call graphs, type references, execution flows, communities, and dead code detection. It answers questions that text search can't: "what breaks if I change this?", "what calls this function?", "is this code reachable?"
MCP Tools Reference
| Tool | What it does | When to use |
axon_query | Hybrid search (text + semantic + fuzzy) grouped by execution flow | Finding relevant code by concept, not just name |
axon_context | 360° view of a symbol — callers, callees, types, dead code status | Understanding a symbol's full dependency web before modifying it |
axon_impact | Blast radius grouped by depth with confidence scores | Before changing a function/class — see what breaks |
axon_dead_code | All unreachable symbols by file | Cleaning up after refactors, verifying nothing was orphaned |
axon_detect_changes | Maps a git diff to affected symbols and flows | During verification — did the changes touch everything they needed to? |
axon_list_repos | Lists indexed repositories with stats | Checking if a repo is indexed and current |
axon_cypher | Read-only Cypher queries against the knowledge graph | Advanced structural queries not covered by other tools |
When to Use at Each Stage
Planning
axon_queryto explore the codebase by concept ("authentication", "payment processing")axon_contexton key symbols to understand existing architecture before designing changesaxon_impactto assess risk of proposed changes and inform phase ordering
Execution
axon_contextbefore modifying any symbol — understand callers, callees, and type dependenciesaxon_impactbefore changing a function's signature or behavior — check the blast radius- Use impact results to identify tests and call sites that need updating alongside your change
Verification
axon_detect_changesto map the phase's diff to affected symbols and execution flowsaxon_dead_codeto check if refactors orphaned any codeaxon_impactto verify all affected call sites were updated
Bug Fixing
axon_contextto trace callers and callees around the buggy symbolaxon_impactto understand what a fix might breakaxon_queryto find related code when the bug's root cause isn't in the obvious location
Re-indexing
If the MCP server runs with axon serve --watch, the index stays current automatically (file-local phases update immediately, global phases batch every 30 seconds). A full re-index is only needed after:
- A large merge or rebase while watch mode was not running
- Switching branches with significant structural changes
To re-index: axon analyze . (or axon analyze --full to skip incremental logic).
Checking Availability
Before relying on Axon tools, verify the index exists:
- Run
axon_list_reposto check if the current repo is indexed - If not indexed, inform the user and suggest running
axon analyze .
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
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.