Autonomous software delivery for AI agents. 18 skills that turn the lifecycle into bounded, self-correcting, checkpoint-resumable phases with deterministic enforcement hooks and a self-improving learn/map loop. For Claude Code and Codex.
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Prove a claim before acting on it: spawn N independent skeptics prompted to REFUTE it (optionally through distinct lenses — correctness, reproduction, security, regression, measurement) and keep it only if a majority fails. Fails closed on ties. Use to gate findings before fixing, fixes before committing, and any…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Implement a whole DAG plan autonomously — one approved pass, one clean rollback point per task, never building on a broken base. It requires an approved plan (specced upstream) and a clean git baseline, takes a SINGLE human approval of the plan, then walks the DAG layer by layer: for each task it implements on an…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
A wrong or bloated learning poisons every future run — this skill's failure mode is worse than learning nothing. Non-negotiable.
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
This skill mutates durable project memory — the files every future session trusts. Non-negotiable.
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Make code measurably faster without breaking it: metric + reproducible baseline FIRST, profile to the real hotspots, then per hotspot apply a change and re-benchmark — kept ONLY if the win is real beyond variance AND correctness holds; otherwise reverted. Stops at the target or diminishing returns. Never accepts an…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Turn a spec into a self-reviewed DAG of atomic build tasks: each task gets acceptance criteria, a disjoint write scope (≤3 files), and a slice-scoped validate; dependencies are wired and layered topologically so nothing builds on a missing base. Adversarial critics then attack the graph (cycles, phantom paths…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Review a change across every dimension at once, then keep only the findings that survive an adversarial check — autonomously. It fans out independent reviewers over the diff (correctness, security, performance, maintainability/readability, test adequacy, API/contract & compatibility), dedups their findings, and puts…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Take verified work to shippable — autonomously, with fail-closed gates and a human sign-off on anything irreversible. It runs the pre-launch gate (final validate green, review clean, security/observability/ rollback checks), and a gate that DIDN'T actually run is treated as a blocker, never as clean. Then it prepares…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Reduce a change's complexity WITHOUT changing behavior, provably: find duplication/dead code/over-abstraction in the diff, apply the smallest clarifying edit, then prove behavior preserved (tests green + adversarial semantic check) or REVERT — looping until dry. Respects Chesterton's Fence: never removes code whose…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Turn a raw feature request into a grounded, TESTABLE spec — autonomously. It recons the real repo and domain to ground every claim, drafts a spec (objectives, user-visible behavior, acceptance criteria, explicit non-goals, constraints, interfaces, risks), then runs a completeness-critic loop that adversarially hunts…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Raise test health to a green, MEANINGFUL suite: find untested behaviors, write real tests, loop-until-green — with every added test MUTATION-CHECKED (break the code, the test must fail; tautologies rejected). Fails closed: never games the suite green (a skill-scoped hook mechanically blocks .skip/.only/suppressions in…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Run the whole engineering lifecycle end-to-end from one request — spec → plan → build → simplify → test → review → performance → ship — as a single autonomous pass with ONE human approval (the plan) and hard-gated escalation for anything irreversible. It chains the auto- phase skills, carries a durable pipeline…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
The discipline that keeps an autonomous run from becoming a runaway: before any unattended loop or workflow, declare the five stop conditions — done-condition, hard cap, token/time budget, no-progress rule, escalation triggers — then hold the run to them and stop the instant one fires. Fails closed: a capped run…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Make long autonomous work durable and resumable: a live .ulpi/runs/ .json status file (per-unit + per-phase state, atomic locked writes via the bundled scripts/checkpoint.mjs CLI) that a resume reads to SKIP everything already done — session-independent. Status writes are non-fatal observability. Use for any…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Run a bounded, self-correcting loop that drives code toward a target state and STOPS honestly — until-green (validate → diagnose → minimal fix → re-run) or until-dry (find → act → re-find until N dry rounds). Every loop declares a termination set (done-condition, max iterations, budget, no-progress stop) and compiles…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Cover a large work-list in parallel without losing correctness or honesty — scout the items inline, then run each through its stages concurrently (map, optionally reduce) via the Workflow tool, with concurrency caps, per-item isolation where items mutate files, and an explicit account of anything dropped. Use when the…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Stand up a recurring scheduled agent for standing work (triage, monitoring, audits, digests): a self-contained IDEMPOTENT brief (each run wakes memory-less and must dedup prior work), a cadence matched to how often work actually arrives, a per-run BOUND, escalation rules, and a teardown condition. For durable…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Wait on an EXTERNAL signal the harness can't notify you about — CI, a deploy, a queue, an endpoint — polling on a cache-aware cadence (≤270s active, ≥1200s idle, never 300s), bounded by a deadline, acting on the transition. Prefers a NATIVE wait/monitor capability when present; when polling must cross a turn it…