ddmitry/adversarial-review
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
6 Commits 1 Branch 0 Tags
834a74c798cb4f6f5275d9a328b74f4a2ab62c5e
Commit Graph
6 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
ddadminandClaude Opus 4.6 834a74c798 docs: document Plan Mode and resume sandbox limitations 
- Add Plan Mode /tmp write limitation to SKILL.md (Step 4) and README
- Document that `codex exec resume` inherits sandbox from original session
- Remove none/low reasoning effort options (minimum is now medium)
- Add .claude to .gitignore (plan files from testing)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-06 22:50:26 +03:00
ddadminandClaude Opus 4.6 0b8891e19e fix: prompt delivery через stdin и захват session ID 
- Зачем:
  - длинные XML-промпты (60+ строк) ломали shell quoting при inline-передаче в codex exec.
  - session ID терялся из-за 2>/dev/null на stderr, делая resume невозможным.
- Что:
  - промпт записывается в temp-файл, передаётся через stdin: `codex exec ... - < file`.
  - stderr перенаправлен в temp-файл, session ID извлекается через grep.
  - resume унифицирован: тот же stdin-механизм вместо inline-аргумента.
  - fallback fresh exec явно обновляет CODEX_SESSION_ID.
  - cleanup дополнен новыми temp-файлами (prompt, stderr).
- Проверка:
  - smoke test: plan review → 2 раунда с resume через session ID — OK.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-06 21:16:06 +03:00
ddadminandClaude Opus 4.6 649256517e feat: translate SKILL.md to English, add permissions guide 
- Why:
  - English makes the skill accessible to a wider audience
  - Permission prompts on every git/codex call hurt UX
- What:
  - Translated all SKILL.md instructions and rules to English
  - Added recommended permissions section to README
  - Removed literal ## from output_format to avoid Claude Code
    security warning about # in quoted arguments
  - Removed overly broad Bash(codex *) permission rule
  - Added explicit note about codex exec scope limitations
- Verify:
  - /adversarial-review produces structured output with markdown headers
  - No "Newline followed by #" security warning on codex exec

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-03 20:06:22 +03:00
ddadminandClaude Opus 4.6 515820abed fix: verdict parsing, README claims, example consistency 
Fixes from adversarial code-vs-plan review (3 rounds):
- Verdict format in prompts now matches parser (bare tokens)
- Missing verdict treated as parse failure, not approval
- README: softened backend swappability to "designed for extensibility"
- Example: replaced incorrect FK scenario with valid transaction bug
- Example: aligned fixes and round-2 summary with round-1 finding

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-03 19:24:56 +03:00
ddadminandClaude Opus 4.6 b86a1778e6 feat: adversarial prompt rewrite + README + example 
- Rewrite all review prompts with XML-structured adversarial stance
  (role, operating_stance, attack_surface, finding_bar, calibration)
- Rename skill from codex-review to adversarial-review
- Add verbatim output rule for reviewer findings
- Improve resume prompt with adversarial re-review focus
- Add README with installation, usage, architecture, roadmap
- Add synthetic example of review output
- Inspired by openai/codex-plugin-cc (Apache-2.0) prompt structure

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-03 18:29:15 +03:00
ddadminandClaude Opus 4.6 7c130253b1 chore: initial import of codex-review skill 
Baseline copy of the working codex-review SKILL.md from dotfiles
before adversarial prompt rewrite and rebranding.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-03 18:25:46 +03:00