aios-codemap-ops
Quick reference for code-review-graph (CRG) MCP tools. Use when you need to look up a CRG tool name, parameter, or pattern. For workflow guidance, see AGENTS.md decision checkpoints. Requires `aios internal codemap install`.
- License 许可
- MIT
- 所属仓库
- rexleimo/aios
- 最近更新
- 2026-11-07
- Stars
- ★ 62
- Forks
- 11
01 前言 Front Matter
- name
- aios-codemap-ops
- tags
- [ "aios", "codemap", "code-review", "crg", "reference" ]
- scopes
- [ "global", "project" ]
- clients
- [ "codex", "claude", "gemini", "opencode", "hermes", "workbuddy", "pi", "zcode", "qoder" ]
- description
- Quick reference for code-review-graph (CRG) MCP tools. Use when you need to look up a CRG tool name, parameter, or pattern. For workflow guidance, see AGENTS.md decision checkpoints. Requires `aios internal codemap install`.
- repoTargets
- [ "codex", "claude", "gemini", "opencode", "hermes", "workbuddy", "pi", "zcode", "qoder" ]
- defaultInstall
- { "global": true, "project": false }
- installCatalogName
- aios-codemap-ops
03 SKILL.md 正文
CRG Tool Quick Reference
Install/Doctor Targets
aios internal codemap install --client all should make CRG available to the AIOS-supported clients:
| Client | Config written |
|---|---|
| Codex | ~/.codex/config.toml ([mcp_servers.code-review-graph]) |
| Claude Code | <project>/.mcp.json |
| Gemini CLI | <project>/.gemini/settings.json |
| OpenCode | ~/.config/opencode/opencode.json plus plugins/crg-plugin.ts |
If a client cannot see CRG tools, run aios internal codemap doctor --fix --client <client> from the target project, then restart that client.
Structured-plan context candidates
When you know a structured-plan task's implementation target, do not ask a human to hand-author every supporting context reference.
- Call AIOS MCP
aios_plan_taskwithaction: "propose_context", the activetask_id, and workspace-relativetargetswhen the task has no targets yet. - AIOS derives a durable proposal from the target plus CRG callers, callees/imports, and tests. This proposal is reviewable only; it does not alter
.aios/planning/active.json. - Present the refs and reasons to the human. Ask a human to activate all candidates with
aios plan task <id> --confirm-context-candidates, or select a subset by repeating--candidate-ref <ref>; this is an explicit process step, not an identity/authentication boundary. - Only after confirmation may you say that the task has active execution context or invoke context-dependent orchestration.
query_graph patterns
| Pattern | Returns |
|---|---|
callers_of |
Functions that call the target |
callees_of |
Functions called by the target |
imports_of |
Imports from a file/module |
importers_of |
Files that import a file/module |
children_of |
Nodes contained in a file/class |
tests_for |
Tests covering the target |
inheritors_of |
Classes inheriting from target |
file_summary |
All nodes in a file |
refactor_tool modes
| Mode | Action |
|---|---|
rename |
Preview rename across all locations |
dead_code |
Find unreferenced symbols |
suggest |
Community-driven refactoring suggestions |
Confidence tiers
| Tier | Meaning |
|---|---|
EXTRACTED |
Certain — directly parsed from code |
INFERRED |
Likely — deduced from patterns |
AMBIGUOUS |
Guess — low confidence |
detail_level
- minimal (default): summary + counts + key entity names
- standard: full output with node/edge details
Always start with minimal. Escalate to standard only when insufficient.
Key tool parameters
| Tool | Key params |
|---|---|
get_minimal_context |
task (required) |
detect_changes |
base, detail_level, changed_files |
get_impact_radius |
changed_files, max_depth, detail_level |
get_review_context |
base, detail_level, include_source |
get_affected_flows |
changed_files, base |
semantic_search_nodes |
query, kind, limit |
query_graph |
pattern, target, detail_level |
traverse_graph |
query, mode (bfs/dfs), depth, token_budget |
find_large_functions |
min_lines, kind, file_path_pattern |
get_architecture_overview |
(none) |
get_hub_nodes |
top_n |
get_bridge_nodes |
top_n |
get_knowledge_gaps |
(none) |
get_surprising_connections |
top_n |
get_suggested_questions |
(none) |
04 同仓库更多 Skills
versioning-by-impact
Use when completing a task and deciding whether repository changes require a semantic version bump and changelog entry before commit/push.
verification-loop
Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.
typesafe-ai
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.
skill-opt-lite
Train and optimize skill documents using the SkillOpt methodology — the agent acts as both target and optimizer, running tasks, reflecting on failures, proposing edits, and validating improvements in a self-contained training loop. TRIGGER: optimize skill, train skill, improve skill, skill training, skill optimization, SkillOpt, skill evolution, skill iteration loop, skill feedback loop, skill tuning.
skill-constraints
Enforce browser automation safety constraints — tool usage order, anti-detection rules, screenshot discipline, and human-in-the-loop checks. Use when setting up or verifying browser/MCP tool operations, NOT for every skill execution.
seo-geo-page-optimization
Use when improving a single page for SEO and AI answer-engine visibility (GEO), especially when you need faster first-screen conversion and clearer traffic funnels.