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 agentmods add skills/hhamja/claude-code-harness/loop-cinpx skills add hhamja/claude-code-harness --skill loop-cigit clone --depth 1 https://github.com/hhamja/claude-code-harnessWhat 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 | $0.00021 | $0.00562 |
| Opus 5 | $0.00010 | $0.00281 |
| Sonnet 5 | $0.00004 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
loop-ci 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 yesterday.
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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
loop-ci — scaffold CI from the loop's own checks
Generate .github/workflows/loop-ci.yml so CI runs the SAME test/lint/build the loop verifies — CI and the loop can never disagree. Detection is yours (the agent's); the workflow text comes from ${CLAUDE_PLUGIN_ROOT}/scripts/gen_ci.sh, a pure, golden-tested generator.
Idempotency: if .github/workflows/loop-ci.yml already exists, print its path and stop. Never overwrite.
Scope today: node projects (npm / pnpm / yarn / bun) are fully supported. Other stacks: see step 4.
Steps
-
Stop if it exists. If
.github/workflows/loop-ci.ymlis present, show the path and end — do not regenerate. -
Detect the commands. Prefer
.claude/loop/loop.config.md(test:/lint:/build:lines). If it is missing, readpackage.jsonscriptsdirectly. Pass a value through verbatim even if it isTODO: ...— the generator comments that step out so the gap stays visible rather than silently dropping it. -
Detect the package manager from the lockfile:
pnpm-lock.yaml→pnpm,package-lock.json→npm,yarn.lock→yarn,bun.lockb/bun.lock→bun. If several exist, prefer the most recently modified; if none, default to npm and say so in the report. -
Non-node projects. If there is no
package.json, this command does not yet emit a workflow for your stack (python/go/rust setup is not implemented). Stop and tell the user, pointing atscripts/gen_ci.shas the place to extend. Never emit a workflow that cannot run. -
Generate:
mkdir -p .github/workflows "${CLAUDE_PLUGIN_ROOT}/scripts/gen_ci.sh" \ --pm <detected> --test "<test>" --lint "<lint>" --build "<build>" \ > .github/workflows/loop-ci.ymlPassing an empty or
TODOvalue is fine — it becomes a commented-out step. -
Report: the created path, any TODO steps still to fill, and the next step. The workflow triggers on
pull_requestandpushto main. Committing and pushing is the user's call — this command only writes the file.
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.
- yesterday First seen · 35 lines · 21 tokens per session scan A 12d35d23fd4c
loop-ci is a skill published in the GitHub repository hhamja/claude-code-harness (1 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 562 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
git-commit-convention
写 git 提交信息、整理提交历史时使用——Conventional Commits 的格式、类型选择和拆分原则。.
delegate-to-deepseek
默认把中等及以下、批量、重复或机械任务作为完整逻辑单元派给 DeepSeek，并由主 Agent 独立验收。适用于批量改文件、扫日志、翻译、ETL、脚本、测试、文档、CRUD、单领域重构、单组件或单 endpoint。主 Agent 可基于上下文和失败代价调整派工策略；用户显式指令、安全、权限、隐私边界和派工后验证不可突破。DEEPSEEKMODE=off 时跳过。.
code-review-checklist
审查代码改动（review diff / PR）时使用——按固定清单过正确性、边界、错误处理和测试盲区，避免只看顺眼不顺眼。.
sruja-project
Procedural workflows for working with the Sruja codebase. Teaches AI editors how to add components, validate changes, and follow patterns.
grill-me
This skill ensures AI and human share a design concept before writing code.
sruja-harness
Verification harness for any AI agent skill. Use with any other skills; before marking a task done, run verify-task. On failure, record a correction learning. Ensures lint, tests, drift, and intent checks pass regardless of which skill generated the code.