From b8336332719f95d392cbd93f417a762a9f82220c Mon Sep 17 00:00:00 2001
From: jdalton <john.david.dalton@gmail.com>
Date: Mon, 27 Apr 2026 10:59:01 -0400
Subject: [PATCH 1/3] chore: env allowlist + .cache exclude + CLAUDE.md fleet
 rules

Doc/config-only updates split out from PR #620.

CLAUDE.md
  - Sync sorting + open-PR + paths + inclusive-language + Set
    constructor sort + don't-revert-untouched rules from the fleet
  - Replace whitelist/blacklist with allowlist/denylist
  - Document workflow-dispatch rule

.config/tsconfig.check.json
  - Restore .cache/** exclude (was previously dropped)

.gitignore
  - Add **/.cache/

.claude/agents/security-reviewer.md
.claude/skills/security-scan/SKILL.md
  - Sync from socket-repo-template canonical

No runtime behavior changes.
---
 .claude/agents/security-reviewer.md   |  4 +-
 .claude/skills/security-scan/SKILL.md |  1 +
 .config/tsconfig.check.json           |  2 +-
 .gitignore                            |  3 ++
 CLAUDE.md                             | 73 +++++++++++++++++++++++++++
 5 files changed, 80 insertions(+), 3 deletions(-)

diff --git a/.claude/agents/security-reviewer.md b/.claude/agents/security-reviewer.md
index a5625045..6ae10889 100644
--- a/.claude/agents/security-reviewer.md
+++ b/.claude/agents/security-reviewer.md
@@ -4,7 +4,7 @@ Apply these rules from CLAUDE.md exactly:
 
 **Safe File Operations**: Use safeDelete()/safeDeleteSync() from @socketsecurity/lib/fs. NEVER fs.rm(), fs.rmSync(), or rm -rf. Use os.tmpdir() + fs.mkdtemp() for temp dirs. NEVER use fetch() — use httpJson/httpText/httpRequest from @socketsecurity/lib/http-request.
 
-**Absolute Rules**: NEVER use npx, pnpm dlx, or yarn dlx. Use pnpm exec or pnpm run with pinned devDeps.
+**Absolute Rules**: NEVER use npx, pnpm dlx, or yarn dlx. Use pnpm exec or pnpm run with pinned devDeps. # zizmor: documentation-prohibition
 
 **Work Safeguards**: Scripts modifying multiple files must have backup/rollback. Git operations that rewrite history require explicit confirmation.
 
@@ -12,7 +12,7 @@ Apply these rules from CLAUDE.md exactly:
 
 1. **Secrets**: Hardcoded API keys, passwords, tokens, private keys in code or config
 2. **Injection**: Command injection via shell: true or string interpolation in spawn/exec. Path traversal in file operations.
-3. **Dependencies**: npx/dlx usage. Unpinned versions (^ or ~). Missing minimumReleaseAge bypass justification.
+3. **Dependencies**: npx/dlx usage. Unpinned versions (^ or ~). Missing minimumReleaseAge bypass justification. # zizmor: documentation-checklist
 4. **File operations**: fs.rm without safeDelete. process.chdir usage. fetch() usage (must use lib's httpRequest).
 5. **GitHub Actions**: Unpinned action versions (must use full SHA). Secrets outside env blocks. Template injection from untrusted inputs.
 6. **Error handling**: Sensitive data in error messages. Stack traces exposed to users.
diff --git a/.claude/skills/security-scan/SKILL.md b/.claude/skills/security-scan/SKILL.md
index 7f2fd77e..0c2cf12e 100644
--- a/.claude/skills/security-scan/SKILL.md
+++ b/.claude/skills/security-scan/SKILL.md
@@ -2,6 +2,7 @@
 name: security-scan
 description: Runs a multi-tool security scan — AgentShield for Claude config, zizmor for GitHub Actions, and optionally Socket CLI for dependency scanning. Produces an A-F graded security report. Use after modifying `.claude/` config, hooks, agents, or GitHub Actions workflows, and before releases.
 user-invocable: true
+allowed-tools: Task, Bash, Read, Grep, Glob
 ---
 
 # Security Scan
diff --git a/.config/tsconfig.check.json b/.config/tsconfig.check.json
index 92fbca1e..02e43cd6 100644
--- a/.config/tsconfig.check.json
+++ b/.config/tsconfig.check.json
@@ -11,5 +11,5 @@
     "verbatimModuleSyntax": false
   },
   "include": ["../**/*.ts", "../**/*.mts"],
-  "exclude": ["../**/node_modules/**/*"]
+  "exclude": ["../**/.cache/**", "../**/node_modules/**/*"]
 }
diff --git a/.gitignore b/.gitignore
index bdcf878e..0aac7108 100644
--- a/.gitignore
+++ b/.gitignore
@@ -59,6 +59,9 @@ desktop.ini
 # store scratch dirs — cleared by pnpm install automatically).
 node_modules
 **/node_modules
+# Defensive cache ignore — Node compile-cache, corepack, and other
+# tools occasionally drop scratch dirs into a project-local .cache/.
+**/.cache/
 
 # Misc temporary/generated files
 Do
diff --git a/CLAUDE.md b/CLAUDE.md
index 550a72dd..a59e46aa 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -29,21 +29,72 @@
 
 - **REQUIRED for staging**: surgical `git add <specific-file> [<file>…]` with explicit paths. Never `-A` / `.`.
 - **If you need a quick WIP save**: commit on a new branch from inside a worktree, not a stash.
+- **NEVER revert files you didn't touch.** If `git status` shows files you didn't modify, those belong to another session, an upstream pull, or a hook side-effect — leave them alone. Specifically: do not run `git checkout -- <unrelated-path>` to "clean up" the diff before committing, and do not include unrelated paths in `git add`. Stage only the explicit files you edited.
 
 The umbrella rule: never run a git command that mutates state belonging to a path other than the file you just edited.
 
 ## 📚 SHARED STANDARDS
 
 - Commits: [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/) `<type>(<scope>): <description>` — NO AI attribution
+- **Open PRs:** when adding commits to an OPEN PR, ALWAYS update the PR title and description to match the new scope. A title like `chore: foo` after you've added security-fix and docs commits to it is now a lie. Use `gh pr edit <num> --title "..." --body "..."` (or `--body-file`) and rewrite the body so it reflects every commit on the branch, grouped by theme. The reviewer should be able to read the PR description and know what's in it without scrolling commits.
 - Scripts: Prefer `pnpm run foo --flag` over `foo:bar` scripts
 - Dependencies: After `package.json` edits, run `pnpm install`
 - Backward Compatibility: 🚨 FORBIDDEN to maintain — actively remove when encountered
 - 🚨 **NEVER use `npx`, `pnpm dlx`, or `yarn dlx`** — use `pnpm exec <package>` or `pnpm run <script>`. Add tools as pinned devDependencies first.
 - **minimumReleaseAge**: NEVER add packages to `minimumReleaseAgeExclude` in CI. Locally, ASK before adding — the age threshold is a security control.
+- 🚨 **NEVER mention private repos or internal project names** in commits, PR titles/descriptions/comments, issues, release notes, or any public-surface text. Internal codenames, unreleased product names, internal tooling repo names not on the public org page, customer names, partner names — none belong in public surfaces. **Omit the reference entirely.** Don't substitute a placeholder ("an internal tool", "a downstream consumer", etc.) — the placeholder itself is a tell that something is being elided. Rewrite the sentence to not need the reference at all.
+- 🚨 **NEVER trigger Publish / Release / Provenance / Build-Release workflows** — no `gh workflow run`, `gh workflow dispatch`, or `gh api .../dispatches`. Workflow dispatches are irrevocable: Publish workflows push npm versions (unpublishable after 24h), Build/Release workflows pin GitHub releases by SHA, container workflows push immutable tags. Even build workflows with a `dry_run` input still treat the dispatch itself as the prod trigger. The user runs workflow_dispatch jobs manually after CI passes on the release commit + tag — Claude **never** dispatches them. If the user asks for a publish, tell them to run the command in their own terminal (or the GitHub Actions UI).
 - File existence: ALWAYS `existsSync` from `node:fs`. NEVER `fs.access`, `fs.stat`-for-existence, or an async `fileExists` wrapper. Import form: `import { existsSync, promises as fs } from 'node:fs'`.
 - Null-prototype objects: ALWAYS use `{ __proto__: null, ...rest }` for config, return, and internal-state objects. Prevents prototype pollution and accidental inheritance. See `src/socket-sdk-class.ts` and `src/file-upload.ts` for examples.
 - Linear references: NEVER reference Linear issues (e.g. `SOC-123`, `ENG-456`, Linear URLs) in code, code comments, or PR titles/descriptions/review comments. Keep the codebase and PR history tool-agnostic — tracking lives in Linear.
 
+### Sorting
+
+Sort lists alphanumerically (literal byte order, ASCII before letters). Apply this to:
+
+- **Config lists** — `permissions.allow` / `permissions.deny` in `.claude/settings.json`, `external-tools.json` checksum keys, allowlists in workflow YAML.
+- **Object key entries** — sort keys in plain JSON config + return-shape literals + internal-state objects. (Exception: `__proto__: null` always comes first, ahead of any data keys.)
+- **Import specifiers** — sort named imports inside a single statement: `import { encrypt, randomDataKey, wrapKey } from './crypto.mts'`. Imports that say `import type` follow the same rule. Statement _order_ is the project's existing convention (`node:` → external → local → types) — that's separate from specifier order _within_ a statement.
+- **Method / function source placement** — within a module, sort top-level functions alphabetically. Convention: private functions (lowercase / un-exported) sort first, exported functions second. The first-line `export` keyword is the divider.
+- **Array literals** — when the array is a config list, allowlist, or set-like collection. Position-bearing arrays (e.g. argv, anything where index matters semantically) keep their meaningful order.
+
+When in doubt, sort. The cost of a sorted list that didn't need to be is approximately zero; the cost of an unsorted list that did need to be is a merge conflict.
+
+### Paths: One Path, One Reference
+
+**If a path appears in two places, that's a bug.** Every artifact (build output, cache directory, generated file, config location) lives at exactly one canonical location, and that location is defined in exactly one place — typically a `paths.mts` (or equivalent path helper) module. Everything else — other scripts, READMEs, Dockerfiles, workflows, tests — derives from that source. No hand-assembled `path.join(...)` strings outside the module that owns them.
+
+- **Within a package**: every script imports its own path module. No script computes paths from raw segments.
+- **Across packages**: when package B consumes package A's artifact, B imports A's path module (or a typed helper exported from it) — never reconstructs the path from string segments. The classic failure: A adds a new path segment (e.g. inserts a `wasm/` directory), B's hand-built copy of the path drifts, builds break.
+- **Doc strings**: README "Output:" lines and `@fileoverview` comments describe the path; they don't _encode_ it for tools to parse. The doc is for humans only — and even there, it must match what the path module actually produces, verified by running the function.
+- **Workflows / Dockerfiles**: GitHub Actions YAML and Dockerfiles can't `import` TS, so they're allowed to reference the path string directly — but they MUST add a comment pointing at the canonical path module so the next person editing knows where the source of truth lives, and any path string must match the module byte-for-byte. If you find yourself writing the same path twice in one workflow, hoist it to a step output or a job-level env var; reference that everywhere downstream.
+- **Comments that re-state the path**: forbidden. A comment like `// Path mirrors getBuildPaths(): build/<mode>/<arch>/out/Final/...` is duplication wearing a comment costume. The import statement is the comment.
+
+When you spot duplication, the answer is never "update both" — the answer is "delete one and import the other." Fix the architecture, not the symptom.
+
+### Inclusive Language
+
+Use precise, neutral terms over historical metaphors that imply hierarchy or exclusion. The substitutes are not euphemisms — they're more _accurate_ (a list of allowed values genuinely is an "allowlist"; "whitelist" is a metaphor that hides what the list does).
+
+| Replace                          | With                                                |
+| -------------------------------- | --------------------------------------------------- |
+| `whitelist` / `whitelisted`      | `allowlist` / `allowed` / `allowlisted`             |
+| `blacklist` / `blacklisted`      | `denylist` / `denied` / `blocklisted` / `blocked`   |
+| `master` (branch, process, copy) | `main` (branch); `primary` / `controller` (process) |
+| `slave`                          | `replica`, `worker`, `secondary`, `follower`        |
+| `grandfathered`                  | `legacy`, `pre-existing`, `exempted`                |
+| `sanity check`                   | `quick check`, `confidence check`, `smoke test`     |
+| `dummy` (placeholder)            | `placeholder`, `stub`                               |
+
+Apply across **code** (identifiers, comments, string literals), **docs** (READMEs, CLAUDE.md, markdown), **config files** (YAML, JSON), **commit messages**, **PR titles/descriptions**, and **CI logs** you control.
+
+Two exceptions where the legacy term must remain (because changing it breaks something external):
+
+- **Third-party APIs / upstream code**: when interfacing with an external API field literally named `whitelist`, keep the field name; rename your local variable. E.g. `const allowedDomains = response.whitelist`.
+- **Vendored upstream sources**: don't rewrite vendored code (`vendor/**`, `upstream/**`, `**/fixtures/**`). Patch around it if needed.
+
+When you encounter a legacy term during unrelated work, fix it inline — don't defer.
+
 ### Promise.race in loops
 
 **NEVER re-race the same pool of promises across loop iterations.** Each call to `Promise.race([A, B, ...])` attaches fresh `.then` handlers to every arm; a promise that survives N iterations accumulates N handler sets. See [nodejs/node#17469](https://github.com/nodejs/node/issues/17469) and `@watchable/unpromise`.
@@ -73,6 +124,27 @@ Emojis allowed sparingly: 📦 💡 🚀 🎉. Prefer text-based symbols for ter
 
 ---
 
+### 1 path, 1 reference
+
+**A path is _constructed_ exactly once. Everywhere else _references_ the constructed value.**
+
+Referencing a single computed path many times is fine — that's the whole point of computing it once. What's banned is _re-constructing_ the same path in multiple places, because that's where drift is born.
+
+- **Within a package**: every script imports its own `scripts/paths.mts` (or `lib/paths.mts`). No `path.join('build', mode, ...)` outside that module.
+- **Across packages**: when package B consumes package A's output, B imports A's `paths.mts` via the workspace `exports` field. Never `path.join(PKG, '..', '<sibling>', 'build', ...)`.
+- **Workflows, Dockerfiles, shell scripts**: they can't `import` TS, so they construct the string once and reference it everywhere downstream. Workflows: a "Compute paths" step exposes `steps.paths.outputs.final_dir`; later steps read `${{ steps.paths.outputs.final_dir }}`. Dockerfiles/shell: assign once to a variable / `ENV`, reference by name thereafter. Each canonical construction carries a comment naming the source-of-truth `paths.mts`. **Re-building** the same path in a second step is the violation, not referring to the constructed value many times.
+- **Comments**: may describe path _structure_ with placeholders ("`<mode>/<arch>`") but should not encode a complete literal path string. The import statement IS the comment.
+
+Code execution takes priority over docs: violations in `.mts`/`.cts`, Makefiles, Dockerfiles, workflow YAML, and shell scripts are blocking. README and doc-comment violations are advisory unless they contain a fully-qualified path with no parametric placeholders.
+
+**Three-level enforcement:**
+
+- **Hook** — `.claude/hooks/path-guard/` blocks `Edit`/`Write` calls that would introduce a violation in a `.mts`/`.cts` file at edit time.
+- **Gate** — `scripts/check-paths.mts` runs in `pnpm check`. Fails the build on any violation that isn't allowlisted in `.github/paths-allowlist.yml`.
+- **Skill** — `/path-guard` audits the repo and fixes findings; `/path-guard check` reports only; `/path-guard install` drops the gate + hook + rule into a fresh repo.
+
+The mantra is intentionally short so it sticks: **1 path, 1 reference**. When in doubt, find the canonical owner and import from it.
+
 ## 🏗️ SDK-SPECIFIC
 
 ### Architecture
@@ -173,6 +245,7 @@ Configs live in `.config/`:
 - Type properties: required first, then optional; alphabetical within groups
 - Class members: 1) private properties, 2) private methods, 3) public methods (alphabetical)
 - Object properties & destructuring: alphabetical (except semantic ordering)
+- `Set` constructor arguments: `new Set([...])` literals are alphanumeric (runtime is order-insensitive)
 
 ### Testing
 

From 7a0a01e645b3344c654659155f54353c6ea114b0 Mon Sep 17 00:00:00 2001
From: jdalton <john.david.dalton@gmail.com>
Date: Mon, 27 Apr 2026 12:22:21 -0400
Subject: [PATCH 2/3] chore(skills): narrow allowed-tools to specific commands

Replaces blanket Bash/Grep/Glob entries with command-pattern-specific
matchers (Bash(prefix:*)) so the skill cannot run anything the body
of the skill doesn't actually invoke. Drops Grep/Glob from skills
that don't use them.

- security-scan: Task, Read, Bash(pnpm exec agentshield:*),
  Bash(zizmor:*), Bash(command -v:*),
  Bash(find .cache/external-tools/zizmor:*)
- updating: Read, Edit, Bash(pnpm run:*), Bash(pnpm test:*),
  Bash(git status:*), Bash(git diff:*), Bash(git add:*),
  Bash(git commit:*), Bash(git log:*)

Addresses billxinli's review on PR #624 / #1283.
---
 .claude/skills/security-scan/SKILL.md | 2 +-
 .claude/skills/updating/SKILL.md      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/.claude/skills/security-scan/SKILL.md b/.claude/skills/security-scan/SKILL.md
index 0c2cf12e..10a3ac3f 100644
--- a/.claude/skills/security-scan/SKILL.md
+++ b/.claude/skills/security-scan/SKILL.md
@@ -2,7 +2,7 @@
 name: security-scan
 description: Runs a multi-tool security scan — AgentShield for Claude config, zizmor for GitHub Actions, and optionally Socket CLI for dependency scanning. Produces an A-F graded security report. Use after modifying `.claude/` config, hooks, agents, or GitHub Actions workflows, and before releases.
 user-invocable: true
-allowed-tools: Task, Bash, Read, Grep, Glob
+allowed-tools: Task, Read, Bash(pnpm exec agentshield:*), Bash(zizmor:*), Bash(command -v:*), Bash(find .cache/external-tools/zizmor:*)
 ---
 
 # Security Scan
diff --git a/.claude/skills/updating/SKILL.md b/.claude/skills/updating/SKILL.md
index f97d5548..159199ec 100644
--- a/.claude/skills/updating/SKILL.md
+++ b/.claude/skills/updating/SKILL.md
@@ -2,7 +2,7 @@
 name: updating
 description: Updates all npm dependencies to their latest versions. Triggers when user asks to "update dependencies", "update packages", or prepare for a release.
 user-invocable: true
-allowed-tools: Bash, Read, Grep, Glob, Edit
+allowed-tools: Read, Edit, Bash(pnpm run:*), Bash(pnpm test:*), Bash(git status:*), Bash(git diff:*), Bash(git add:*), Bash(git commit:*), Bash(git log:*)
 ---
 
 # updating

From 8c6ebbd08be2f46af4e61c785c20132dbac2a048 Mon Sep 17 00:00:00 2001
From: jdalton <john.david.dalton@gmail.com>
Date: Mon, 27 Apr 2026 14:45:50 -0400
Subject: [PATCH 3/3] chore(claude): add tools: frontmatter to agents,
 deny-list to settings, allowed-tools to quality-scan

Extends the .claude/ tightening already on this branch:

- Adds tools: frontmatter to all three agents so they declare exactly
  what they need instead of inheriting the default tool set:
  - code-reviewer (read-only): Read, Grep, Glob, Bash(git/rg/grep/find/ls/wc/cat/head/tail:*)
  - security-reviewer: same + Bash(pnpm exec agentshield:*), Bash(zizmor:*),
    Bash(command -v:*)
  - refactor-cleaner: adds Edit, Write, Bash(pnpm run/test/exec:*), Bash(node:*)
- Adds permissions.deny block to .claude/settings.json blocking
  publish/release escape hatches: npm/pnpm/yarn publish, gh release
  create/delete, gh workflow run/dispatch, git push --force/-f.
  Particularly important for socket-sdk-js, which publishes to npm
  but currently has no Bash-targeted PreToolUse hooks.
- Adds allowed-tools: to quality-scan/SKILL.md (was missing entirely,
  inheriting full default access).

Mirrors the canonical pattern landed on socket-repo-template main.
---
 .claude/agents/code-reviewer.md      |  6 ++++++
 .claude/agents/refactor-cleaner.md   |  6 ++++++
 .claude/agents/security-reviewer.md  |  6 ++++++
 .claude/settings.json                | 13 +++++++++++++
 .claude/skills/quality-scan/SKILL.md |  1 +
 5 files changed, 32 insertions(+)

diff --git a/.claude/agents/code-reviewer.md b/.claude/agents/code-reviewer.md
index 1e05e099..c30d6aa7 100644
--- a/.claude/agents/code-reviewer.md
+++ b/.claude/agents/code-reviewer.md
@@ -1,3 +1,9 @@
+---
+name: code-reviewer
+description: Reviews code in socket-sdk-js against CLAUDE.md rules and reports style violations, logic bugs, and test gaps. Spawned by the quality-scan skill or invoked directly on a diff.
+tools: Read, Grep, Glob, Bash(git:*), Bash(rg:*), Bash(grep:*), Bash(find:*), Bash(ls:*), Bash(wc:*), Bash(cat:*), Bash(head:*), Bash(tail:*)
+---
+
 You are a code reviewer for a Node.js/TypeScript monorepo (socket-sdk-js).
 
 Apply the rules from CLAUDE.md sections listed below. Reference the full section in CLAUDE.md for details — these are summaries, not the complete rules.
diff --git a/.claude/agents/refactor-cleaner.md b/.claude/agents/refactor-cleaner.md
index ee62c149..ea507d4e 100644
--- a/.claude/agents/refactor-cleaner.md
+++ b/.claude/agents/refactor-cleaner.md
@@ -1,3 +1,9 @@
+---
+name: refactor-cleaner
+description: Refactor specialist for socket-sdk-js. Removes dead code first, batches changes into ≤5-file phases, verifies each with the project's check + test scripts. Use after quality-scan or before structural refactors.
+tools: Read, Edit, Write, Grep, Glob, Bash(git:*), Bash(rg:*), Bash(grep:*), Bash(find:*), Bash(ls:*), Bash(pnpm run:*), Bash(pnpm test:*), Bash(pnpm exec:*), Bash(node:*), Bash(cat:*), Bash(head:*), Bash(tail:*)
+---
+
 You are a refactoring specialist for a Node.js/TypeScript monorepo (socket-sdk-js).
 
 Apply these rules from CLAUDE.md exactly:
diff --git a/.claude/agents/security-reviewer.md b/.claude/agents/security-reviewer.md
index 6ae10889..1d35eabd 100644
--- a/.claude/agents/security-reviewer.md
+++ b/.claude/agents/security-reviewer.md
@@ -1,3 +1,9 @@
+---
+name: security-reviewer
+description: Reviews findings from AgentShield + zizmor against socket-sdk-js's CLAUDE.md security rules and grades the result A-F. Spawned by the security-scan skill after the static scans run.
+tools: Read, Grep, Glob, Bash(git:*), Bash(rg:*), Bash(grep:*), Bash(find:*), Bash(ls:*), Bash(pnpm exec agentshield:*), Bash(zizmor:*), Bash(command -v:*), Bash(cat:*), Bash(head:*), Bash(tail:*)
+---
+
 You are a security reviewer for Socket Security Node.js repositories.
 
 Apply these rules from CLAUDE.md exactly:
diff --git a/.claude/settings.json b/.claude/settings.json
index ac130fc1..6ff9cfe0 100644
--- a/.claude/settings.json
+++ b/.claude/settings.json
@@ -11,5 +11,18 @@
         ]
       }
     ]
+  },
+  "permissions": {
+    "deny": [
+      "Bash(gh release create:*)",
+      "Bash(gh release delete:*)",
+      "Bash(gh workflow dispatch:*)",
+      "Bash(gh workflow run:*)",
+      "Bash(git push --force:*)",
+      "Bash(git push -f:*)",
+      "Bash(npm publish:*)",
+      "Bash(pnpm publish:*)",
+      "Bash(yarn publish:*)"
+    ]
   }
 }
diff --git a/.claude/skills/quality-scan/SKILL.md b/.claude/skills/quality-scan/SKILL.md
index d204ca29..909dd584 100644
--- a/.claude/skills/quality-scan/SKILL.md
+++ b/.claude/skills/quality-scan/SKILL.md
@@ -1,6 +1,7 @@
 ---
 name: quality-scan
 description: Runs comprehensive quality scans across the codebase using specialized agents to identify critical bugs, logic errors, caching issues, and workflow problems. Use when improving code quality, before releases, or investigating issues.
+allowed-tools: Task, Skill, Read, Edit, Grep, Glob, AskUserQuestion, Bash(pnpm run check:*), Bash(pnpm run test:*), Bash(pnpm test:*), Bash(pnpm run fix:*), Bash(git status:*), Bash(git diff:*), Bash(git log:*), Bash(git add:*), Bash(git commit:*), Bash(rg:*), Bash(grep:*), Bash(find:*), Bash(ls:*)
 ---
 
 # quality-scan