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.
git clone --depth 1 https://github.com/codesstar/lociWrote 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/commands/codesstar/loci/loci-sync)<a href="https://agentmods.dev/commands/codesstar/loci/loci-sync"><img src="https://agentmods.dev/badge/commands/codesstar/loci/loci-sync/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/commands/codesstar/loci/loci-sync"><img src="https://agentmods.dev/badge/commands/codesstar/loci/loci-sync.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 | $0.00000 | $0.00064 |
| Opus 5.5 | $0.00000 | $0.00026 |
| Sonnet 5.5 | $0.00000 | $0.00013 |
| Haiku 4.5 | $0.00000 | $0.00006 |
Grade A, and why
loci-sync 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 8d 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.
What it actually says
先定位已连接大脑，完整读取并遵守 LOCI-RULES.md（当前上下文已有且未变时复用）。
按用户指定范围整理本轮有持久价值的信息；--dry-run 时仅预览，不写入；--local 时只更新当前项目。
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.
- 8d ago Changed · -121 lines 43351b10a2e5
- 1mo ago First seen · 125 lines · 0 tokens per session scan A 7528b7fd6677
loci-sync is a command published in the GitHub repository codesstar/loci (508 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 64 tokens. 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 commands, from other repositories
ensoul
Activate Claudicle soul identity in this session. Creates a per-session marker so soul.md, soul state, and session awareness persist through compaction and resume.
tag
Attach manual keyword metatags to the current Claude Code session. These tags supplement the auto-generated Qwen tags in /.claude/session-registry.json and are searchable via /claude-tracker-search --name (and, after the Phase 2 default-mode pre-pass, via the bare /claude-tracker-search ).
quote-search
Search notable phrases captured via /quote or auto-extracted from sessions. Uses FTS5 full-text search or tag-based filtering.
gpd:compact-state
Archive historical entries from STATE.md to keep it under the 150-line target.
gpd:resume-work
Resume research from previous session with full context restoration.
gpd:record-insight
Record a project-specific learning or pattern to the insights ledger.