One reported bug, reproduced on the unchanged build, re-run blind by a second agent, fixed at its invariant with a failing-first regression test and a single signed-off local commit, then proven on baseline, patched and reverted worktrees by yet another agent. Records, receipts and hash manifests stay in $TMPDIR; nothing is pushed.
Plugin patching-bugs from marketplace devops in flyoverhead/devops-plugins. Commands read from the repo's manifest — today.
implement-patchRepairs one confirmed bug where its invariant breaks, inside the finding's repair_scope — before-repair gate, a hunt for same-invariant variants, suite before and after, a regression test seen failing on the unpatched code first, the smallest reviewable fix, then one local `git commit -s` plus fix.p
patching-bugsDrives one named bug from report to a local fix commit that someone other than its author has proven — intake into finding.json, a reproduce agent, a blind validate agent, up to three patch-then-prove rounds by separate fresh agents, an optional regression-hunt pass, and a Markdown report with a ver
prove-patchJudges a new local fix commit without trusting its author — every repair_scope case through one retained side-blind harness on clean baseline and patched worktrees, the project checks that matter on both, then the three-arm check (baseline fails, patch passes, patch reset to baseline fails again) —
reproduce-bugShows one reported bug is real on the current build before any edit — builds the pinned baseline in a scratch worktree with the project's own command, runs the built artifact through a PoC harness printing PATCH_LOADED, PATCH_CASE and PATCH_REACHED (or the exact compiler diagnostic), and stores its
validate-bugRepeats a reproduce-bug package as a second, independent observer — same pinned baseline and recorded build argv in a fresh worktree, the unchanged PoC on the same inputs, only the files and never the reproducer's transcript — and records confirmed, not_confirmed or inconclusive in validate.json wit
Go toolkit: version-aware idioms, concurrency fixes proven with the race detector, performance work backed by benchmarks and profiles, read-only code review, tests that match the repository, a GitHub-ready project scaffold and gopls LSP.
5 skills · 3 agents · hooks · LSP
Did a PR, commit or commit range break something that used to work? Pins the before and after states, hunts candidate regressions in the diff, then has three separate fresh agents reproduce, replay and adjudicate each one on live S0 and S1 builds. Sealed evidence, an attempt registry and an HTML/Markdown/JSON report stay in a campaign directory outside the repo; GitHub is only read.
7 skills
Ansible toolkit: role creator in the classic upstream layout (install/configure/service, meta/argument_specs.yml, sentence-case names, true/false, FQCN, ansible-lint production profile), role checker and molecule scaffolder, plus a guard on real ansible-playbook runs
3 skills · 1 agent · hooks
Terraform toolkit: module-creator for YAML-driven modules with inheritance and validation layers (OpenStack, VMware, AWS, Azure, GCP, Proxmox), provider-creator for Plugin Framework providers with a GitHub Actions release, plus terraform-ls LSP and safety hooks
2 skills · 1 agent · hooks · LSP
Settles whether suspected security findings tied to a code location are real: restates each claim, traces source to sink, proves or refutes attacker control and impact, writes PoCs outside the repo without running them, and passes six gates before a TRUE or FALSE POSITIVE verdict. Takes scanner output, review findings or a pasted GitHub code-scanning alert.
1 skill · 3 agents
API design and review: OpenAPI 3.1 specs, REST and GraphQL patterns, OWASP API Security Top 10 review with Spectral and Redocly linting
1 skill · 1 agent · hooks
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
hooks
Cross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails
3 skills · 1 command · 1 agent
Install the "AAS Security Engineer" editorial skill bundle for Claude Code.
12 skills
Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture
24 skills · 2 agents
SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening
5 skills · 3 commands · 2 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.