LoopX is a provider-neutral control plane that gives long-running AI-agent work persistent state, decisions, governance, recovery, and handoffs across different agent harnesses. It is for managing and reviewing durable work performed by Codex, Claude Code, Cursor, dsh, or custom agent systems.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add huangruiteng/loopx --skill loopx-self-repairgit clone --depth 1 https://github.com/huangruiteng/loopxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huangruiteng/loopx/loopx-self-repair)<a href="https://agentmods.dev/skills/huangruiteng/loopx/loopx-self-repair"><img src="https://agentmods.dev/badge/skills/huangruiteng/loopx/loopx-self-repair/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huangruiteng/loopx/loopx-self-repair"><img src="https://agentmods.dev/badge/skills/huangruiteng/loopx/loopx-self-repair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00102 | $0.01860 |
| Opus 5.5 | $0.00041 | $0.00744 |
| Sonnet 5.5 | $0.00020 | $0.00372 |
| Haiku 4.5 | $0.00010 | $0.00186 |
Grade A, and why
loopx-self-repair scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LoopX Self Repair
Use this skill to turn a surprising LoopX behavior into a durable fix, not only an apology or a one-off explanation.
Repair Loop
-
Pause delivery selection. Do not spend quota or continue adapter work until the control-plane facts explain why that work is valid.
-
Build a compact evidence packet. Prefer structured surfaces:
git status --short --branch loopx --format json diagnose --goal-id <goal-id> loopx --format json status --goal-id <goal-id> --limit 20 loopx --format json quota should-run --goal-id <goal-id> [--agent-id <agent-id>] loopx --format json history --goal-id <goal-id> --limit 5statusdefaults to the registry/dashboard view, but accepts--goal-idwhen the repair needs one goal-focused projection. Usediagnose --goal-idfor the richer goal-specific agent reasoning packet. Also inspect the project-local registry and the registry-declared active state file when relevant. Use the shared global registry for heartbeat/quota truth. -
Classify the failure. Read
references/repair-patterns.mdand match the symptoms to a known pattern. If no pattern fits, add one after the fix. -
Assign the responsible layer. Separate:
- agent behavior mistake;
- state projection or quota payload bug;
- active-state authoring gap;
- benchmark harness mismatch;
- docs/process hygiene gap.
-
Repair at the lowest durable layer.
- If it is a one-off agent mistake, write back the correct state/todo and size the next scoped effort to its verifiable result, evidence and risk.
- If the machine projection misled the agent, fix CLI/status/quota projection and add a focused smoke.
- If the user correction changes the goal acceptance, says the agent missed
the intended loop, or exposes a product bottleneck that is not visible in
quota/status, write a bounded
goal_vision_replan_contract_v0packet withreplan_trigger_summarythrough normalloopx refresh-state --vision-*fields, using the same--agent-idas the current lane, or--agent-vision-jsonfor generated multi-field patches, before returning to delivery. If the next executable step is already known, also add or link the concrete successor todo; do not leave the correction only in chat or an incident note. - If a design rule is missing, update the interaction model or todo list before implementing broad behavior.
- If benchmark evidence is not attributable, add posthoc trace/parity checks before claiming uplift or regression.
-
Validate before resuming. Run the smallest smoke or CLI check that would have caught the issue, plus
loopx checkon changed public surfaces when docs/contracts changed. -
Write back the lesson. Update active goal state, docs, contributor tasks, or this skill so the same failure mode is visible next time.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +1 lines a816fca69aea
- 1mo ago First seen · 158 lines · 102 tokens per session scan A 57c1f7f03695
loopx-self-repair is a skill published in the GitHub repository huangruiteng/loopx (6,356 stars, last pushed 6d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,860 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
log-analyzer
Use when parsing agent log files to identify error patterns, rate limit hits, timeout clusters, tool failures, and component-level error counts. Produces a structured anomaly report. Cron-compatible — silent if no issues, alert digest if anomalies found.
huawei-cloud-agentarts-obs-diagnosis
Observability no-data diagnosis skill for Huawei Cloud AgentArts agent-ops platform. Systematically diagnoses missing metrics, logs, and traces/sessions in agent-ops by checking subscription metadata, data pipeline (APM/AOM/LTS), query parameters, and authentication. Generates root-cause analysis and fix…
b3os-ai-code-safety
As code and logic grow, the cost is not the happy path — it is coupling: a change ripples into places you did not touch, and a "small fix" breaks something unrelated. This skill is a code-structure and refactoring guide: structure well from the initial design so a change stays local, apply operational safety where…
endpoint-probe
Use when you need to discover an API's surface — poke a base URL to find its type (REST, GraphQL, SOAP, JSON-RPC), auth scheme, available endpoints, rate limits, and CORS policy. Also probes MCP servers (HTTP and stdio) to discover tools, resources, and prompts with full input schemas. Runs a Python probe script that…
refire
Turns confirmed findings from a taste into one scoped fix run, then re-verifies each finding at its cited location. Use after /sous-chef:taste when the user says to fix the findings, apply the review, or refire it. Not for new feature work - that is a fresh /sous-chef:fire.
loop-detection
Use when identifying and preventing infinite loops, detecting loop patterns, implementing loop exit strategies, and creating loop safety mechanisms. Includes loop analysis, timeout patterns, and loop monitoring. Based on programming best practices and loop safety patterns.