keelwright

Engine for vibe-coders and loop-coders who ship AI-generated code they can't read line by line. Covers 28 known failure modes: SQL injection, hardcoded secrets, hallucinated packages (slopsquatting), reward hacking (AI deletes tests to pass), doom loops (runaway token burn), false reports, missi

as observed 2026-09-02T06:49:02.991Z

Want to know when this changes? Sign in with an email address and we will tell you. Free, no card, watch up to 5.

Identifier: keelwright
Source: ClawHub
Version observed: 1.11.0
Source repository: not published
Repository observation: No source repository listed
First observed here: 2026-08-28T22:06:28.212Z
Observations recorded: 5
Installs (reported upstream): 2
Weekly downloads (upstream): 1,453

Observation history

2026-09-02T06:49:02.991Z

Fields that differed: changelog displayName latestVersion

Field	Before	After
`changelog`	"v1.10.0: layered skill (ADR-001), SKILL.md 17K->3K tokens, 84% reduction. Build script for registries."	"v1.11.0: SkillSpector response bundle (permissions, viral opt-in, verify_web_guard tighten, strategy move, QA gating)"
`displayName`	"Keelwright Fix"	"keelwright"
`latestVersion`	"1.10.0"	"1.11.0"

2026-09-01T06:16:18.534Z

Fields that differed: changelog latestVersion

Field	Before	After
`changelog`	"Hotfix: remove Hermes venv hardcode, runtime-agnostic (KEELWRIGHT_SKILLS, find_skills_dir, ~/.keelwright default)."	"v1.10.0: layered skill (ADR-001), SKILL.md 17K->3K tokens, 84% reduction. Build script for registries."
`latestVersion`	"1.9.1"	"1.10.0"

2026-08-31T05:56:02.339Z

Fields that differed: changelog latestVersion

Field	Before	After
`changelog`	"Wave 2 audit fixes: T11 ACTIVE-after-verify, T13 userinfo redact, T14 MEDIUM advisory, T15 breaker.py, T16 model-pin, F29 Cursor/Codex/Cline/OpenClaw bindings, honest framing	"Hotfix: remove Hermes venv hardcode, runtime-agnostic (KEELWRIGHT_SKILLS, find_skills_dir, ~/.keelwright default)."
`latestVersion`	"1.8.0"	"1.9.1"

2026-08-29T23:02:09.653Z

Fields that differed: changelog description displayName latestVersion summary

Field	Before	After
`changelog`	"v1.7.1: privacy fix — removed all operator-private repo/path references (lazy-unicorn/SETUP_GUIDE.md, hardcoded C:/Users/Unicorn paths). Skill now fully self-contained + runt	"Wave 2 audit fixes: T11 ACTIVE-after-verify, T13 userinfo redact, T14 MEDIUM advisory, T15 breaker.py, T16 model-pin, F29 Cursor/Codex/Cline/OpenClaw bindings, honest framing
`description`	"Engine for vibe-coders and loop-coders who ship AI-generated code they can't read line by line. Covers 28 known failure modes: SQL injection, hardcoded secrets, hallucina	"Engine for vibe-coders and loop-coders who ship AI-generated code they can't read line by line. Covers 28 known failure modes: SQL injection, hardcoded secrets, hallucina
`displayName`	"keelwright"	"Keelwright Fix"
`latestVersion`	"1.7.1"	"1.8.0"
`summary`	"Engine for vibe-coders and loop-coders who ship AI-generated code they can't read line by line. Covers 28 known failure modes: SQL injection, hardcoded secrets, hallucina	"Engine for vibe-coders and loop-coders who ship AI-generated code they can't read line by line. Covers 28 known failure modes: SQL injection, hardcoded secrets, hallucina

Correction

If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.