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/implement)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/implement"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/implement/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/implement"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/implement.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 | $0.00037 | $0.09168 |
| Opus 5.5 | $0.00015 | $0.03667 |
| Sonnet 5.5 | $0.00007 | $0.01834 |
| Haiku 4.5 | $0.00004 | $0.00917 |
Grade A, and why
implement 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 — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.
implement
根据 ${FEATURE_DIR}/tasks.md 中的任务分解与 design 技术计划，按阶段、依赖与 TDD 要求在工作区代码树中执行实施，并产出任务执行报告。
环境初始化
本节子步骤编号为 1、2、3（整数），与下方「指令」区 步骤 0–11 独立，勿混用。
本技能所有路径解析与脚本调用均依赖以下变量。代码改动落在 CLAUDE_WORKING_DIR 指向的工程树内（可与 Git 仓库根不同，例如子目录工作区）。
| 变量 | 含义 | 用途 |
|---|---|---|
CLAUDE_PLUGIN_ROOT |
Omni 插件安装根目录 | check-prerequisites、workflow-gate 等 |
CLAUDE_WORKING_DIR |
用户当前工作区目录 | 工程根、.cache/、.gitignore 等横切文件 |
FEATURE_DIR |
当前特性目录 | tasks.md、design.md、制品与 checklists |
工作区路径约定
| 符号 | 展开路径 |
|---|---|
| 任务清单 | ${FEATURE_DIR}/tasks.md |
| 设计 | ${FEATURE_DIR}/design.md 或 IMPL_DESIGN（来自 env.sh / JSON） |
| 规范 | ${FEATURE_DIR}/spec.md |
| E2E 实现设计（可选） | ${FEATURE_DIR}/e2e-impl-design.md |
| 代码质量综合评测采集JSON | ${FEATURE_DIR}/.runs/evaluations/code.diff.json |
| 代码质量综合评测报告 | ${FEATURE_DIR}/.runs/evaluations/eval-code-report.txt |
| 检查清单目录 | ${FEATURE_DIR}/checklists/ |
| 上下文成本日志 | ${CLAUDE_WORKING_DIR}/.cache/context_cost.log |
| Harness 环境 | ${FEATURE_DIR}/.runs/env.sh |
1. 检查变量
test -n "${CLAUDE_PLUGIN_ROOT:-}" && test -d "${CLAUDE_PLUGIN_ROOT}"
test -n "${CLAUDE_WORKING_DIR:-}" && test -d "${CLAUDE_WORKING_DIR}"
任一项失败 → 执行 步骤 2 补全。
2. 补全变量
CLAUDE_WORKING_DIR 缺失时：
export CLAUDE_WORKING_DIR="$(pwd)"
不用 git rev-parse --show-toplevel。
3. 校验
test -f "${CLAUDE_PLUGIN_ROOT}/scripts/bash/check-prerequisites.sh"
test -d "${CLAUDE_WORKING_DIR}"
mkdir -p "${CLAUDE_WORKING_DIR}/.cache"
推荐（workflow 进入 implement 前通常已具备）：
source "${FEATURE_DIR}/.runs/env.sh"
路径拼接约定
- 插件脚本：
${CLAUDE_PLUGIN_ROOT}/scripts/bash/...、${CLAUDE_PLUGIN_ROOT}/scripts/powershell/... check-prerequisites须在CLAUDE_WORKING_DIR下执行，且带--require-tasks --include-tasks- 禁止仅用 Git 分支或裸
check-prerequisites猜FEATURE_DIR（优先paths.json/env.sh） - workflow 编排方可在 implement 前后调用：
${CLAUDE_PLUGIN_ROOT}/scripts/bash/workflow-gate.sh --feature-dir "$FEATURE_DIR" --check <pre-implement|post-implement|...>
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 First seen · 524 lines · 37 tokens per session scan A db42537adbfe
implement is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (57 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 9,168 once invoked, about $0.0001 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
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.