atrislabs/engines
atris/skills/engines/SKILL.md
Dispatch coding work to an installed terminal agent — Codex, Cursor, or Devin — as an interchangeable worker engine. Claude orchestrates: writes the bounded prompt, the engine builds, Claude verifies and lands. Triggers on: use codex, use cursor, use devin, engine, dispatch to, worker agent, second opinion build.
$ install --global
skillsauthnpx skillsauth add atrislabs/atris enginesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 13, 2026, 4:00 AM37.1s1 file scanned
SKILL.md
- name:
- engines
- description:
- Dispatch coding work to an installed terminal agent — Codex, Cursor, or Devin — as an interchangeable worker engine. Claude orchestrates: writes the bounded prompt, the engine builds, Claude verifies and lands. Triggers on: use codex, use cursor, use devin, engine, dispatch to, worker agent, second opinion build.
- version:
- 1.0.0
Engines — interchangeable terminal workers
One contract, three engines. The orchestrator (you, Claude) writes a bounded task prompt, dispatches it to an engine, then independently verifies, lands, and pushes the result. Engines never self-certify.
Invocation
| Engine | Command | Notes |
|--------|---------|-------|
| Codex | node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task --background [--write] "<prompt>" (via codex plugin / codex:codex-rescue agent) | Poll with status, fetch with result <job-id> |
| Cursor | cursor-agent --trust -p "<prompt>" (run from the target repo) | Headless print mode; --trust required for non-interactive |
| Devin | devin -p --permission-mode dangerous -- "<prompt>" (run from the target repo) | Default permission mode is read-only for writes — build work NEEDS --permission-mode dangerous, so only run it in an isolated worktree. Also devin cloud for sessions that outlive this machine |
Picking an engine
- Codex — deep root-cause work, long autonomous builds, second-opinion diagnosis. Slowest; runs sandboxed.
- Cursor — fast bounded edits and refactors in a single repo.
- Devin — multi-step feature work; use
cloudwhen the run should survive laptop sleep. - Parallel builds across repos: one engine job per repo, never two engines writing the same checkout.
Prompt contract (every dispatch)
- Name the absolute repo path and tell the engine to
cdthere. - Bound the slice: one task, explicit exit criteria, the verify command to run.
- Git rules:
git statusfirst; stage only own files; never revert others' changes; never destructive git; work on a branchmember/<name>-<slug>or a worktree. - Require a final report: files changed, verify command + result, branch name.
Landing (orchestrator duties — never skip)
- Codex sandbox cannot reach github.com and may get read-only repo access. Expect temp clones /
git format-patchfallbacks under/private/tmp. Apply patches in a fresh worktree, re-run the verify command yourself, then push. - Cursor and Devin run unsandboxed — still re-run the verify command yourself before pushing.
- Engine task DBs and receipts written inside a sandbox are snapshots; reconcile against the live
atris taskplane after landing. - A stalled job (no log output for 30+ min) gets cancelled and taken over; don't wait on it.
Related Skills
atrislabs/wake
development
VerifiedTrustedCommunity
Wake a team member by name — 'gm <member>' or 'wake up <member>' — and run ONE closed-loop tick: boot, inbox, claim, one bounded slice, verify, commit+push, proof, receipt. Optionally dispatch the build to an engine (codex/cursor/devin). Triggers on: gm, good morning, wake up <member>, wake the team, run a tick as <member>.
63SKILL.mdUpdated Jun 13, 2026
atrislabs/tune
development
VerifiedTrustedCommunity
Live RL tuner for skills. Watches skill invocations, reads user reaction, proposes targeted SKILL.md overlay edits, requires explicit approval, writes scorecards. The in-session half of the skill-RL loop (Path B). Triggers on: tune, sharpen, skill feedback, that was shit, that was great, make X better.
61SKILL.mdUpdated Apr 18, 2026
atrislabs/improve
development
VerifiedTrustedCommunity
Run one RL improvement tick on the workspace via POST /api/improve. Ships one verifiable change, scores it, writes the scorecard. The thing you pay for. Triggers on: improve, make this better, ship one thing, run a tick, get smarter.
61SKILL.mdUpdated Apr 12, 2026
atrislabs/copy-editor
testing
VerifiedTrustedCommunity
Detects AI slop and fixes it, especially in memos, docs, READMEs, messages, PRDs, and other written output. Based on Wikipedia's AI Cleanup patterns plus memo-specific anti-slop rules. Triggers on "copy edit", "review writing", "humanize", "deslopper", "ai patterns", "make it sound human", "AI slop", "anti-slop", "memo".
61SKILL.mdUpdated Apr 3, 2026