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-auditnpx skills add hhamja/claude-code-harness --skill loop-auditgit 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 | $0.00025 | $0.00318 |
| Opus 5 | $0.00013 | $0.00159 |
| Sonnet 5 | $0.00005 | $0.00064 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
loop-audit 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.
What it actually says
loop-audit — principle & gate adherence check
On-demand process audit, complementary to loop-run --verify-only (which grades the product against rubric.md). This grades whether the loop upheld its own method.
If .claude/loop/ does not exist: say so and point to /loopy:loop-init. Otherwise:
- Spawn the
auditoragent with the instruction "audit this loop's process and decision-gate adherence". It reads.claude/loop/and recent git history and returns one## Auditor report(per-principle PASS/FAIL/UNKNOWN + verdict) plus a## Gaps / nextlist. It modifies nothing. - Print the report verbatim.
- Apply it (main agent does the write, mirroring how verifier reports are applied): OVERWRITE
.claude/loop/audit.mdwith the report and a one-line timestamp header.audit.mdis a human-facing artifact — committed likereview.md, not gitignored. - Suggest the next step: address the top gap, or resume with
/loopy:loop-run.
Do not fix anything here yourself beyond writing audit.md; the gaps are for the next loop-run cycle or a human to act on. Safe to run anytime, including as the first command of a fresh session.
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 · 19 lines · 25 tokens per session scan A 1432520346ad
loop-audit is a skill published in the GitHub repository hhamja/claude-code-harness (1 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 318 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.