The-AIE
OrganizationA portable, self-improving SDLC harness for agent fleets — plan → issues → build → test → review → UX-eval → security → ship, on any runtime (Claude Code, Codex, Grok, Hermes). Apache-2.0.
Categories
Indexed Skills (8)
testing-gibson-harness
How to runtime-test The Gibson's bash harness (loop.sh, second-opinion.sh, devin-supervisor.sh) — scratch repos, vendor-CLI auth reality, PATH shims, mock Devin API, and macOS bash 3.2 portability checks.
gibson-audit
Audit any repository for Gibson-readiness: what the product is, stack, test/CI/gate coverage, backlog shape, risk surfaces (money, auth, consent/PII, security boundaries, production data), and a plain-English readiness report with concrete gaps. First stage of the /gibson pipeline; also useful standalone ('audit this repo', 'is this repo ready for the fleet', 'gibson readiness check').
gibson-direct
The owner's product-direction interface to the Gibson: turn plain-English goals into a well-scoped plan and decomposed, acceptance-criteria'd issues the fleet can build from — and answer the fleet's product questions on the owner's behalf where direction already covers them. For owners who don't read code. Trigger: 'here's what I want built', 'product direction', 'turn this into a plan/issues', or when gibson-audit finds no usable backlog.
gibson-resources
Discover which AI runners and infrastructure are actually available right now (Grok/Codex/Claude/Hermes CLIs, Devin API, GitHub auth, bot identities, satellite machines, MCPs) and produce the cost-optimized routing table the Gibson loop will use. Second stage of the /gibson pipeline; also standalone ('what runners do I have', 'fleet inventory', 'check the fleet').
gibson-run
Start and supervise the Gibson development loop against a wired repo: cost-routed runners (Grok volume, Codex second/review, Claude judgment, Devin merge captain), error budgets, escalation, kill switch, and a plain-English digest for the owner. Final stage of the /gibson pipeline; also standalone ('start the loop', 'run the fleet on <repo>', 'resume gibson development').
gibson-setup
Wire a repository for autonomous fleet development: install the Gibson guardrail bundle (AGENTS section, CI gates, labels, branch protection, kill switch) and connect the Devin cloud supervisor as merge captain. Consumes gibson-audit's gap list; idempotent. Third stage of the /gibson pipeline; also standalone ('set up this repo for the fleet', 'gibson-ify this repo', 'install the guardrails').
gibson
Point The Gibson at any repo and run the full autonomous development loop — audit the repo, discover which AI runners/resources are available, set up GitHub guardrails, then drive continuous build/test/review/merge with cost-optimized routing (Grok for volume, Codex second, Claude for judgment, Devin as merge captain). The owner's recurring job is product direction in plain English; spend, credentials, and Tier-C merges always come back to them for explicit approval. Trigger on: 'gibson <repo>', 'run the gibson', 'point the gibson at', 'start autonomous development on', 'have the fleet build', or any ask to set up and run the agent-fleet SDLC loop against a repository.
gibson-red-team
Run Gibson's repeatable red-team protocol against a target app to find security, auth, payment, PII/consent, and business-logic flaws before they ship — and before any paid third-party review. First target is ConferenceOS (mrhinkle/conference-os). Produces scored findings, files Critical/High as GitHub issues, and reports a readiness verdict. Use when Mark says "red team the app," "run Gibson," "run the red team," "security sweep," "attack conference-os," "are we secure," or "pre-pentest check."
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.