deadeye-coder
Lean-first coding persona (YAGNI, stdlib-first, shortest diff). Levels: spotter, marksman, sniper.
Quick-reference card for every deadeye command and setting.
$ npx -y skills add deepaksinghcs14/deadeye-cc --skill deadeye-help --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/deadeye-helpContext preview
The summary Claude sees to decide when to auto-load this skill.
Quick-reference card for every deadeye command and setting.
name: deadeye-help description: Quick-reference card for every deadeye command and setting. license: MIT
Present this reference card, formatted cleanly:
| Level | What it does | |---|---| | `spotter` | Builds what's asked, names the leaner alternative in one line | | `marksman` | The lean-first ladder enforced. Default. | | `sniper` | Maximum minimalism — one-liners, challenges the requirement itself |
(writes deadeye's own `~/.deadeye/config.json`, never Claude's settings)
| Command | What it does | |---|---| | `/deadeye-status` | Modes, coder level, kill switches, catalog, daemon health | | `/deadeye-config` | View or change any setting from chat (or just say what to change) | | `/deadeye-route [task]` | Dry-run the routing decision with full reasoning | | `/deadeye-stats [savings\|context]` | Decision-log reports: measured impact (default), token savings, per-session context breakdown | | `/deadeye-coder [level]` | Switch/report the coder persona level | | `/deadeye-mute [off]` | Session-scoped mute for advisories/nags (rewrites stay on) | | `/deadeye-review [--repo]` | Four-lens self-review of the working diff, or the whole repo with `--repo` -- the pre-PR version of `/deadeye-pr` | | `/deadeye-guard` | Security review of the current diff -- full OWASP-mapped coverage (Top 10:2025, API Security Top 10 2023, LLM Top 10:2025), deps | | `/deadeye-vapt` | Whole-service pen-test/VAPT pass -- full OWASP Top 10:2025/API Security Top 10 2023/LLM Top 10:2025 coverage | | `/deadeye-pr [<PR>] [--post]` | PR review across four lenses -- over-engineering, correctness, performance, security | | `/deadeye-sweep [--repo\|--pr [<PR>]] [<N>] [--commit] [--all]` | Applies review/guard findings (crit/high, or every severity with `--all`), verifies the build, loops until clean (cap 5). `--pr` mode also fixes/replies/resolves the PR's own open review comments | | `/deadeye-debt` | Ledger of `deadeye:` shortcut markers | | `/deadeye-help` | This card |
CLI-only: `deadeye lessons [reset]` inspects/clears the recorded routing outcomes that bias future decisions. `deadeye update` updates the managed binary directly (sha256-verified, atomic) — for Codex-only installs.
`~/.deadeye/config.json` (seeded with defaults on first run; project overrides in `.deadeye.json`). Coder knobs: `coder.default_level`, `coder.subagent_matcher`, `coder.injection_budget_tokens`, `coder.security` (`off`/`advise`/`ask`, the live Edit/Write advisory), `coder.security_osv` (`false` keeps the dependency check fully offline).
`/plugin marketplace update deadeye` then `/reload-plugins` — or enable auto-update under `/plugin` → Marketplaces. Codex-only install: run `deadeye update` instead (see CLI-only above).
One-shot: do NOT change any mode or write anything.
Claude Code plugin that fits the model, effort, and context to each task — fewer tokens, same quality. Deterministic policy kernel in the hooks; every number it reports is measured, not estimated.
Lean-first coding persona (YAGNI, stdlib-first, shortest diff). Levels: spotter, marksman, sniper.
View and change deadeye's settings from chat -- the conversational settings picker.
Security review of the current diff -- full OWASP-mapped coverage (Top 10:2025, API Security Top 10 2023, LLM Top 10:2025), injection through auth, config, and…
PR review across four lenses -- over-engineering, correctness, performance, security -- printed locally, opt-in to post.
Four-lens self-review (over-engineering, correctness, performance, security) of the working diff, or the whole repo with --repo.