360 Secure SkillHub
360 安全技能中心

gitnexus-refactoring

该 Skill 指导通过 GitNexus MCP 工具进行安全代码重构:先绑定仓库与工作树,再用影响面分析、上下文查询和语义重命名预览,确认后才应用编辑,最后用变更检测与测试验证;覆盖符号重命名、提取模块和拆分函数或服务。

abhigyanpatwari
热度 0.00
最近更新 2026-10-18 16:02:06
分类:开发依赖:MCP 服务 / 代码执行应用场景:代码生成 / 工作流

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add abhigyanpatwari/gitnexus/gitnexus-refactoring
Metadata
name
gitnexus-refactoring
description
Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file"

Refactoring with GitNexus

When to Use

  • "Rename this function safely"
  • "Extract this into a module"
  • "Split this service"
  • "Move this to a new file"
  • Any task involving renaming, extracting, splitting, or restructuring code

Bind the repository first

Refactoring writes to disk. rename with dry_run: false edits files in whichever repository was resolved, so binding identity here is a safety gate, not bookkeeping.

Call list_repos {} before the first tool call. With one indexed repository, use the examples below as written. With more than one, pass repo on every call: an omitted repo normally errors, but under an MCP policy with a configured default it resolves to that default silently. If you cannot tell which repository is meant, stop and ask. Never run rename with dry_run: false until the preview in the same bound repository has been reviewed — its returned file_path values show which checkout is about to be written, so read them as a confirmation of identity.

list_repos is paginated, so page with offset: pagination.nextOffset until hasMore is false before concluding a repository is absent.

detect_changes takes worktree when you are editing a linked worktree the MCP server was not launched from; otherwise git diff runs in the wrong checkout and reports nothing changed, which reads as a verified refactor.

Workflow

0. list_repos {}                                  → Bind repo (and worktree)
1. impact({target: "X", direction: "upstream"})  → Map all dependents
2. query({search_query: "X"})                            → Find execution flows involving X
3. context({name: "X"})                           → See all incoming/outgoing refs
4. Plan update order: interfaces → implementations → callers → tests

If "Index is stale" → run node .gitnexus/run.cjs analyze in terminal. Hot-tool staleness names which index answered (branch/lastCommit) and how fresh it is (status). Re-analyze only for behind or diverged — current is identity, unknown is unmeasurable.

Checklists

Rename Symbol

- [ ] list_repos {} — bind repo; explicit repo when >1 indexed, ask if ambiguous
- [ ] rename({symbol_name: "oldName", new_name: "newName", dry_run: true}) — preview semantic edits (omitting dry_run also previews)
- [ ] Confirm the previewed file paths are in the bound repository/worktree
- [ ] Review exact graph-backed semantic spans, coverage, and limitations
- [ ] If satisfied: rename({..., dry_run: false, plan_token: "<token from preview>"}) — apply exactly the reviewed edits
- [ ] detect_changes() — verify only expected files changed
- [ ] Run tests for affected processes

Extract Module

- [ ] list_repos {} — bind repo; explicit repo when >1 indexed, ask if ambiguous
- [ ] context({name: target}) — see all incoming/outgoing refs
- [ ] impact({target, direction: "upstream"}) — find all external callers
- [ ] Define new module interface
- [ ] Extract code, update imports
- [ ] detect_changes() — verify affected scope
- [ ] Run tests for affected processes

Split Function/Service

- [ ] list_repos {} — bind repo; explicit repo when >1 indexed, ask if ambiguous
- [ ] context({name: target}) — understand all callees
- [ ] Group callees by responsibility
- [ ] impact({target, direction: "upstream"}) — map callers to update
- [ ] Create new functions/services
- [ ] Update callers
- [ ] detect_changes() — verify affected scope
- [ ] Run tests for affected processes

Tools

rename — semantic rename; preview first, then apply:

rename({symbol_name: "validateUser", new_name: "authenticateUser", repo: "my-app", dry_run: true})
→ 12 edits across 8 files
→ semantic_edits: 12, coverage: {name: "gitnexus-semantic", scope: "indexed-repository", limitations: [...]}
→ changes: [{file_path, edits: [{start, length, line, old_text, new_text, confidence: "semantic"}]}]

dry_run omitted or true previews and never writes; dry_run: false requires the successful preview's plan_token. Keep the same repository, selected symbol, and destination name. Tokens are single-use, expire after 15 minutes or a server restart, and may be evicted when retained previews reach 16 plans or 64 MiB. Any apply attempt consumes the token; request and review a fresh preview to retry. An MCP server started with GITNEXUS_MCP_READ_ONLY=1 still lists rename, but as preview-only: it rejects any dry_run other than omitted or true, so apply through a server that permits writes. Request and review a fresh preview there; tokens belong to the process that issued them.

Rename uses the indexed graph and GitNexus's own semantic layer. Language providers resolve current source through scopes and bindings; no compiler or language service is loaded. Unsupported syntax, ambiguous bindings, stale declarations, and incomplete occurrence coverage fail closed. Coverage describes indexed files accepted by the selected provider, including supported embedded sources, and excludes unindexed files and external consumers. All registered source-language providers supply rename rules. Declaration and override families require complete semantic evidence. Dynamic or computed references block a rename when the provider cannot resolve them or exclude them from the selected family. Provider-specific limits, including class renames requiring a file move, remain explicit in results. There is no regex fallback: legacy graph_edits and text_search_edits are zero. Comments, strings, and unrelated same-spelled symbols are not replacements.

Preview captures the exact semantic plan, source hashes and physical file targets. Apply validates that plan and executes its edits without replanning. Changes to indexed targets, source bytes or paths (including newly added untracked source files) reject the plan before writing. Unindexed files remain outside semantic coverage; analyze first when they need refactoring. Results use result_version: 2; total_edits counts occurrences, not matching lines. Exact replacements are shown in new_text. Check planning_status, application_status, and applied. A completed apply has status: "success", application_status: "applied", and applied: true. A successful preview has not written files. rename does not accept branch: it inspects the current checkout.

Recover from a blocked or incomplete rename before applying again. A failed result carries code and error; nothing was written unless the last row applies.

Result Next step
stale_graph Re-analyze the bound repository, then preview again with rename (dry_run omitted or true).
source_changed Preview again against the current source and review it. If it appears during an apply, see the partial row.
plan_required, invalid_plan, plan_mismatch Apply needs the successful preview's token and identical repository, symbol and new name. Expired, consumed or evicted plans require a fresh reviewed preview.
source_set_changed Source paths changed, including untracked files. Re-analyze and review a fresh preview.
plan_too_large The captured plan exceeds the 64 MiB retention budget. Narrow the indexed repository before previewing again.
unsupported_* Stop automated rename and inspect the reported limitation. Use a language-aware manual refactor if needed.
Ambiguous target (status: "ambiguous" with candidates) Inspect the returned candidates or context, then preview with the chosen symbol_uid.
ambiguous_reference, incomplete_semantics The planner could not prove a reference, import, or declaration is covered. Stop automated rename; resolve the named location by hand or pick a different symbol.
name_collision new_name would collide with, or change the identity of, another declaration or binding. Choose a different name and preview again.
invalid_name new_name is empty, equals the current name, or is not valid in the target language. Choose a valid, different identifier.
invalid_argument dry_run was sent but is not a boolean. Omit it or send true or false.
no_locations The planner produced no edits. Do not apply; re-check the target with context and pass symbol_uid.
overlapping_edits, invalid_edit The planned spans conflict or do not match the source text. The plan is rejected before any write; do not apply. Refactor manually or report the case.
duplicate_file, missing_snapshot, outside_repository A planner safety check failed (two paths resolve to one real file, a file has no source snapshot, or a path leaves the repository). Re-analyze and preview again; if it repeats, stop and report it.
source-unavailable (reason: "content-retention" or "checkout-missing") The index was built without full source retention (GITNEXUS_CONTENT_RETENTION), or the checkout directory is missing. Re-analyze with full retention, or run against the checkout.
rename_failed An unexpected error while planning, before any write (application_status: "not_started"). Re-analyze and preview once more; if it repeats, stop and report the error text.
application_status: "partial" or "failed" (write_failed, or source_changed mid-apply) Writes are not transactional. Inspect landed changes (already written, with their counts), failed_files (the one file whose write or validation failed), and unattempted_files (later files never touched). Reconcile the current files, re-index, and review a fresh preview; never blindly retry the apply call.

Run the project validation suite after applying.

impact — map all dependents first:

impact({target: "validateUser", repo: "my-app", direction: "upstream"})
→ d=1: loginHandler, apiMiddleware, testUtils
→ Affected Processes: LoginFlow, TokenRefresh

detect_changes — verify your changes after refactoring:

detect_changes({scope: "all"})
→ Changed: 8 files, 12 symbols
→ Affected processes: LoginFlow, TokenRefresh
→ Risk: MEDIUM

partial: true (a graph query failed) or truncated: true (the changed-symbol listing was capped) means the result is short of the truth: a short or empty list is not proof that only the expected files changed. Re-run it rather than treat the refactor as verified.

A wrong-worktree zero carries neither flag and is indistinguishable from a clean verification, so confirm the diffed checkout is the one you edited.

cypher — custom reference queries:

MATCH (caller)-[:CodeRelation {type: 'CALLS'}]->(f:Function {name: "validateUser"})
RETURN caller.name, caller.filePath ORDER BY caller.filePath

Risk Rules

Risk Factor Mitigation
Many callers (>5) Use rename for automated updates
Cross-area refs Use detect_changes after to verify scope
String/dynamic refs query to find them
External/public API Version and deprecate properly
Same name in another indexed repo Bind repo; verify previewed paths before applying

Example: Rename validateUser to authenticateUser

0. list_repos {}
   → total: 2 (my-app, billing-api) — both define validateUser, so bind explicitly

1. rename({symbol_name: "validateUser", new_name: "authenticateUser", repo: "my-app", dry_run: true})
   → 12 semantic occurrences in the indexed repository's supported provider scope
   → Files: validator.ts, login.ts, middleware.ts...

2. Review semantic spans and provider coverage; inspect dynamic references separately

3. rename({symbol_name: "validateUser", new_name: "authenticateUser", repo: "my-app", dry_run: false, plan_token: "<token from step 1>"})
   → Applied 12 edits across 8 files

4. detect_changes({scope: "all", repo: "my-app"})
   → Affected: LoginFlow, TokenRefresh
   → Risk: MEDIUM — run tests for these flows
   Repository: my-app (/abs/path/my-app)  Worktree: same  Index: current

With a single indexed repository, step 0 returns total: 1 and the repo argument drops out of every call above.