Commit Graph
2 Commits
Author SHA1 Message Date
Pawel HurynandClaude Opus 5 18032bc9f7 pm-ai-shipping: code-review becomes the top-level skill; perf + security are sub-cases
Restructure, per the ask that code review be the parent and the other two
dimensions its sub-cases:

- SKILL.md gains a "one engine, three anchors" section. Correctness is the
  core and stays inline; performance and security move to their own reference
  files, loaded only when selected.
- references/performance-review.md (new) — a universal, stack-agnostic core
  (repeated work, growth relationships, retention, copying, contention,
  amplification) plus the three-part bar for a performance finding. Defers the
  database/web checklist to /performance-audit-static instead of restating it.
- references/security-review.md (new) — trust boundaries and sinks for code
  with no web surface, and the one rule that INVERTS relative to correctness:
  attacker-equals-victim refutes a security finding but never a correctness
  one. Defers the full procedure to /security-audit-static.
- Both audit commands now say they are the specialisation behind their
  sub-case, so the narrow entry points still lead back to the skill.

ship-check gains two stages it was missing:

- Step 3, correctness review — the pass neither audit performs: logic and
  state defects that compile clean and pass the suite.
- Step 6, independent unsteered review — a fresh session of a second model
  (Codex or equivalent), given no checklist and no prior findings, with the
  subject computed from a diff rather than described. Every finding is
  hand-verified against the code before it enters the packet, since an
  unsteered reviewer carries no refutation discipline of its own. The packet
  reports whether it ran clean or did not run at all - those are different
  signals.

Also carries the working-tree edits already in progress: model-and-orchestration
guidance on both audits, the OWASP A02/A06/A09 backstop, CSP in the
output-encoding bullet, the prompt-injection/agent-abuse bullet, and the Audit
Provenance section (now also naming the second model).

No version bump - not tested against the benchmark yet.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01G42vsxSKL7je39AsHZ5aJm
2026-09-13 15:15:57 +02:00
Pawel HurynandClaude Opus 4.8 8202bdd7f1 Release v2.0.0: add pm-ai-shipping plugin, red-team execution skill, refresh README
New
- pm-ai-shipping (9th plugin) — AI Shipping Kit: document a vibe-coded app, audit
  security/performance against intended behavior, map test coverage, and compile a
  reviewer-ready shipping packet (2 skills, 5 commands).
- pm-execution: strategy-red-team skill + /red-team-prd command (now 16 skills, 11 commands).

Changed
- Bump all versions 1.0.1 -> 2.0.0 (marketplace.json + all 9 plugin.json) in lockstep.
- README: new plugins.png hero + examples.png in "How It Works"; counts updated to
  9 plugins / 68 skills / 42 commands across tagline, install block, and per-plugin sections.
- CLAUDE.md: 9-plugin structure, plugin table, and version note updated.

Validator: 9 plugins, 68 skills, 42 commands, 110 components, 0 warnings.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-05 18:49:54 +02:00