feat(analyzer): add OpenCode-native SkillSpector invocation skill and tool

[Yoseph-Zuskin]

Add OpenCode-native SkillSpector invocation (/skillspector + tool)

Problem

There is no OpenCode-native way to invoke SkillSpector: no slash command,
no agent-callable tool, so scans require manual CLI use outside the
session.

Fixes: #535

Approach

• Two files, zero new dependencies, no package.json, no plugin module
  (file-based tools/commands auto-discovery handles registration):
  .opencode/tools/skillspector_scan.ts and
  .opencode/commands/skillspector.md.
• Tool skillspector_scan(target, format=json, noLlm=true, output?)
  shells out via stdlib execFile: binary chain SKILLSPECTOR_BIN env,
  then <worktree>/.venv, then bare skillspector on PATH, with an
  install hint on miss; defaults scan <target> --format <format> --no-llm. Mirrors the precedent of extensions/skillspector.ts
  (Pi agent surface: same tool name, redaction, truncation, binary
  chain) — same conventions, different host loader.
• 120s timeout with kill + partial-output report; stdout truncated ~12k
  chars / stderr ~6k; sk-ant-*, sk-*, *_API_KEY/*_TOKEN redacted.
• Exit semantics: 1 with stdout returns the JSON report (findings, not a
  crash); 2 returns stderr as a usage error. /skillspector forwards
  $ARGUMENTS as the target with an LLM opt-in line.
• Defaults to --no-llm for instant static scans; LLM opt-in via
  noLlm=false or SKILLSPECTOR_PROVIDER/MODEL env passthrough.

Verification

• Headless load test (opencode 1.18.x, one inference call):
  /skillspector auto-discovered, agent called
  skillspector_scan {"noLlm":true,"target":"./fixture-skill"}, JSON
  flowed back and was summarized as 0/100 LOW, SAFE, 2 files, 100%
  coverage.
• Zero-inference harness against the same tool file: missing binary
  returns the install hint; timeout kills at 120s with partial output
  and redacted secrets; usage error surfaces stderr; exit-1 risk
  fixture (score 100/CRITICAL) returns parseable JSON head with
  truncation note.
• Python gates N/A on this branch: no Python files changed or added.
• Status (2026-09-14): feat/opencode-plugin on origin; self-scan of
  .opencode/ via opencode_cli: 0/LOW, 0 issues, 3/3 LLM calls.
• Live extension test (2026-09-14, opencode 1.18.30, temp project,
  SKILLSPECTOR_BIN → venv skillspector.exe): /skillspector
  auto-discovered, agent called skillspector_scan, fixture skill
  returned 0/100 LOW, SAFE, 100% coverage. Finding: the host may omit
  the format default, so the tool passed --format undefined
  (exit 2, surfaced cleanly); fixed via args.format ?? "json" /
  args.noLlm ?? true fallbacks (the latter keeps LLM strictly opt-in).
• Unit tests: pure helpers extracted to dependency-free
  .opencode/tools/skillspector_scan_lib.ts, covered by
  tests/opencode/skillspector_scan_lib.test.ts via stdlib node --test
  (18/18, Node 22+ type stripping, zero new deps); headless /skillspector
  regression re-run green after the reshape.

Sample

> /skillspector ./fixture-skill
skillspector_scan {"noLlm":true,"target":"./fixture-skill"} -> 0/100 LOW, SAFE

Risks

• Large reports exceed the ~12k truncation cap (a 17.4k finding report
  came back truncated); consumers needing full JSON should pass output.
• Uses stdlib execFile, not Bun.$, for timeout/kill support; trivial
  to swap if maintainers prefer $.
• DCO: all commits carry Signed-off-by (maintainer: verify on push).

[rng1995]

[SkillSpector Review]

Reviewed current head fc1773a0027f95a92194fe7b9c0c46be2a3bd5d2. The extension is not ready to ship: it allows model-triggered scans of arbitrary host paths and optional LLM egress without an OpenCode permission request, ignores cancellation, mangles supported SCP-style Git targets, documents a nonexistent provider, loses valid exit-2 reports and successful-run warnings, incompletely redacts supported credentials, and its TypeScript tests are not run by required CI. The inline comments give concrete corrections and regressions.

Hosted checks pass, but these required security/correctness/test changes and mergeStateStatus=BEHIND block merging.

[rng1995]

Approved at exact head 586a787 after resolving all eight review threads and rebasing onto current main 2e9ae8d. Verified explicit OpenCode read/edit/external-directory/network/LLM permissions and denial-before-launch; cancellation propagation; SCP/Windows/POSIX target classification; credential redaction and ambient LangChain/LangSmith tracing suppression; bounded stdout/stderr evidence on success and exits 1/2; valid provider documentation; pinned Node 22 TypeScript CI; and symlink/junction defenses for targets, outputs, and explicit/auto executable paths. Focused TypeScript suite passes 44/44, and exact-head changes, lint, test-unit, OpenCode TypeScript Tests, DCO, and docker-smoke checks are all green.

[rng1995]

[SkillSpector Review]

Re-reviewed current head 030937ebf065ca3a2a2cf1d7454d32dbded01818 against all eight prior findings and the later hardening stack. Every prior issue is resolved: capability requests cover local/external reads, report writes, remote targets, explicit LLM egress, executable access, and the subprocess before launch; cancellation reaches the child; supported SCP targets and cross-platform local paths are classified correctly; credential and tracing data are withheld/redacted; stdout and stderr evidence survives success and exits 1/2; documentation names a valid provider; and the pinned Node 22 test lane is green. The additional symlink/junction checks protect local targets, outputs, and explicit/auto executable paths. I found no remaining required code, test, documentation, security, or compatibility changes.

All required checks, including OpenCode TypeScript Tests, are green and all prior threads are resolved. The PR is mergeable but mergeStateStatus=BEHIND after #558, so the current head is not merge-ready; any auto-sync changes the reviewed commit and requires re-review.