Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ZTE-AICloud/Co-OmniSpec/plugin install omni-dsddWrote 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/zte-aicloud/co-omnispec/local-sandbox-fix)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/local-sandbox-fix"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/local-sandbox-fix/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/zte-aicloud/co-omnispec/local-sandbox-fix"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/local-sandbox-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.01926 |
| Opus 5 | $0.00027 | $0.00963 |
| Sonnet 5 | $0.00011 | $0.00385 |
| Haiku 4.5 | $0.00005 | $0.00193 |
Grade A, and why
local-sandbox-fix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Sandbox 自动修复
编排「本地沙盒 CI → 失败分析 → 修码 → omni-dsdd:code-review → 重测」闭环，最多 3 轮。详细设计见 docs/local-sandbox-fix-design.md。
执行主线：环境初始化 → Step 1 init+gate0 → Step 2 主循环（gate 2-start-ci～7-record-iteration，最多 3 轮）。
硬约束
- 工程路径 = CLAUDE_WORKING_DIR（=
run_local_ci.py的 workdir）；禁止git rev-parse --show-toplevel - gate_exit≠0 时不得进入下一步
- gate 2～3 之间禁止修改代码
- 禁止删除文件规避检查
- 所有路径从
source "${HARNESS_DIR}/env.sh"获取 - 禁止绕过 harness 手工执行
pytest、go test、npm test、tox或local-ci；所有本地 CI/test 只能由 gate2-start-ci～7-record-iteration驱动 devops_config.yaml缺失时，gate0-init会写出status=success, skipped=true并结束；此时不得补跑任何测试、不得修代码/测试、不得把普通 UT 通过当成本 stage 结果
环境初始化
进入 Step 1 之前的就绪准备：检查/补全 CLAUDE_PLUGIN_ROOT、CLAUDE_WORKING_DIR，校验 harness 脚本，自动从记录文件解析 FEATURE_DIR（未传 --feature-dir 时由 harness 读取 .active-feature / changes/*/.runs/.omnispec-state.json 等记录，解析不到则报错）。详见 references/stages/00-environment-init.md。
执行契约与产物
编排 / 落盘 / 校验分离：Agent 负责 LLM 修码与 omni-dsdd:code-review；Harness gate 负责 cp、启动 CI、等待、解析 JSON、验 diff、验报告。
| 文件 | 用途 |
|---|---|
${FEATURE_DIR}/.runs/local-sandbox-fix/paths.json |
路径真值源 |
${HARNESS_DIR}/env.sh |
source 后导出绝对路径 |
${HARNESS_DIR}/run-manifest.json |
分步门禁、断点续跑 |
${HARNESS_DIR}/fix-context.json |
CI 失败时修码上下文 |
契约：references/harness-contract.json
Step 1 — init + gate 0-init
主循环（Step 2）的地基：init 只建地基（目录/路径/状态），gate 0-init 做就绪校验 + 文件初始化（devops_config 的 cp / 缺失 skip）。本步不碰业务代码、不跑 CI。若缺失 devops_config.yaml，gate 0-init 已代表本 stage 成功 skip，必须立即停止，不得再执行普通 UT 或自动修复。详见 references/stages/01-init-and-gate0.md。
Step 2 — 主循环
每轮开始前 必须 resume：
python3 "${CLAUDE_PLUGIN_ROOT}/skills/local-sandbox-fix/scripts/python/local_sandbox_fix_harness.py" \
resume --harness-dir "${HARNESS_DIR}"
What ships with it
16 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.
- docs/local-sandbox-fix-design.md 40 KB
- references/fix-guidelines.md 891 B
- references/harness-contract.json 1.5 KB
- references/stages/00-environment-init.md 2.9 KB
- references/stages/01-init-and-gate0.md 2.2 KB
- references/stages/02-run-and-wait-ci.md 862 B
- references/stages/03-analyze-result-and-fix.md 918 B
- references/stages/04-code-review-gate.md 975 B
- references/stages/05-retry-and-exit.md 615 B
- scripts/bash/local-sandbox-fix-common.sh 598 B runs code
- scripts/bash/local-sandbox-fix-gate.sh 326 B runs code
- scripts/bash/local-sandbox-fix-init-harness.sh 1.4 KB runs code
- scripts/bash/local-sandbox-fix-workflow-gate.sh 1.3 KB runs code
- scripts/python/local_sandbox_fix_harness.py 33 KB runs code
- scripts/python/test_local_sandbox_fix_harness.py 13 KB runs code
- scripts/python/wait_sandboxcheck.py 4.4 KB runs code
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.
- 11d ago First seen · 152 lines · 54 tokens per session scan A 9a3b3bbe0e45
local-sandbox-fix is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,926 once invoked, about $0.0003 per session on Opus 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
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.