Skill Claude CodeCodex needs its repo
Crash-resilient external agent loop with state persistence and CI/CD integration.
not rated 224
+1
changed 1mo ago A SkillSpector: warn 18 tokens
original MIT
224Stars on the repository
204Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
agent-loop
02Skill Claude CodeCodex needs its repo
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor.
not rated 224
+1 today A SkillSpector: warn 17 tokens
original MIT
Skill Claude CodeCodex
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern.
not rated 224
+1
changed 1mo ago A SkillSpector: warn 23 tokens
original MIT
Skill Claude CodeCodex
Enable agent loops to learn from similar past tasks and share patterns across loops.
not rated 224
+1
changed 1mo ago A SkillSpector: pass 20 tokens
original MIT
debug-memory
05Skill Claude CodeCodex
Query and manage the executable feedback debug memory.
not rated 224
+1
changed 1mo ago A SkillSpector: pass 11 tokens
original MIT
Skill Claude CodeCodex
Execute tests on generated code and iterate until passing.
not rated 224
+1
changed 1mo ago A SkillSpector: pass 12 tokens
original MIT
Skill Claude CodeCodex
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly.
not rated 224
+1 today A SkillSpector: warn 34 tokens
original MIT
Skill Claude CodeCodex
Orchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions, monitor, and stop.
not rated 224
+1 today A SkillSpector: pass 26 tokens
original MIT
ralph-abort
09Skill Claude CodeCodex
Abort a running agent loop and optionally revert changes.
not rated 224
+1
changed 1mo ago A SkillSpector: warn 14 tokens
original MIT
Skill Claude CodeCodex
Show analytics and metrics from agent loop execution history.
not rated 224
+1
changed 1mo ago A SkillSpector: pass 14 tokens
original MIT
ralph-attach
11Skill Claude CodeCodex
Attach to a running agent loop's live output stream.
not rated 224
+1
changed 1mo ago A SkillSpector: pass 15 tokens
original MIT
ralph-config
12Skill Claude CodeCodex needs its repo
View and configure agent loop settings — show, set, reset, and apply named presets.
not rated 224
+1
changed 1mo ago B SkillSpector: warn 21 tokens
original MIT
Skill Claude CodeCodex needs its repo
Crash-resilient external loop with state persistence and CI/CD integration.
not rated 224
+1
changed 1mo ago A 18 tokens
copy · 91% MIT
ralph-memory
14Skill Claude CodeCodex needs its repo
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.
not rated 224
+1
changed 1mo ago A SkillSpector: warn 21 tokens
original MIT
Skill Claude CodeCodex
View and manage agent loop reflections and episodic memory.
not rated 224
+1
changed 1mo ago A SkillSpector: pass 15 tokens
original MIT
ralph-resume
16Skill Claude CodeCodex needs its repo
Resume an interrupted agent loop from last checkpoint.
not rated 224
+1
changed 1mo ago C 13 tokens
original MIT
ralph-status
17Skill Claude CodeCodex
Check status of current or previous agent loop.
not rated 224
+1
changed 1mo ago C 12 tokens
original MIT
ralph
18Skill Claude CodeCodex
Execute iterative task loop until completion criteria are met - iteration beats perfection.
not rated 224
+1 today A SkillSpector: warn 16 tokens
original MIT
Skill Claude CodeCodex
Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them.
not rated 224
+1
changed 1mo ago A SkillSpector: pass 23 tokens
original MIT
Skill Claude CodeCodex
Enable and explain the reusable human-in-the-loop gates used by persistent agent loops for destructive actions, false-positive overrides, and recovery escalation.
not rated 224
+1 today A SkillSpector: warn 31 tokens
original MIT
Skill Claude CodeCodex
Guide or repair a headless Linux AIWG Cockpit plus Agentic Sandbox deployment when host topology, SSH access, service persistence, or runtime readiness must be planned safely.
not rated 224
+1 today A SkillSpector: pass 41 tokens
original MIT
Skill Claude CodeCodex
Generate a setup.manifest.yaml file for a project using the setup.aiwg.io/v1.
not rated 224
+1 today B SkillSpector: warn 26 tokens
original MIT
setup-run
23Skill Claude CodeCodex
Execute a setup.aiwg.io/v1 SetupManifest, performing cross-platform installati.
not rated 224
+1 today A SkillSpector: warn 21 tokens
original MIT
Skill Claude CodeCodex
Validate a setup.aiwg.io/v1 SetupManifest file against the schema and run cons.
not rated 224
+1 today A SkillSpector: warn 23 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: