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 skills add r0shi/harborclerk --skill harbor-clerkgit clone --depth 1 https://github.com/r0shi/harborclerkWrote 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/r0shi/harborclerk/harbor-clerk)<a href="https://agentmods.dev/skills/r0shi/harborclerk/harbor-clerk"><img src="https://agentmods.dev/badge/skills/r0shi/harborclerk/harbor-clerk/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/r0shi/harborclerk/harbor-clerk"><img src="https://agentmods.dev/badge/skills/r0shi/harborclerk/harbor-clerk.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 | $0.00042 | $0.00450 |
| Opus 5 | $0.00021 | $0.00225 |
| Sonnet 5 | $0.00008 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
harbor-clerk 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 12d 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
Harbor Clerk - extended memory for agents
Harbor Clerk is a local document corpus with hybrid FTS+vector search and citation-ready reads. This skill exposes it via the harbor-clerk CLI.
First step: discover the surface
Run harbor-clerk --help for the full command list, then harbor-clerk <cmd> --help for any specific command. The help is comprehensive: JSON return shapes, examples, and common mistakes are all there.
Four patterns you'll use most
- Search → expand:
harbor-clerk search "..."thenharbor-clerk expand-context <chunk_id> -n 3on the best hit. - Find every matching document:
harbor-clerk find-all "..." --text-contains "literal phrase" --presentation fullwhen the task asks to list or enumerate. - Read a known document:
harbor-clerk read-document <doc_id>for full text with pagination. - Check ingest status before searching for new content:
harbor-clerk ingest-status <doc_id>returns per-stage state.
What you can trust
- Search returns top-level
.hits[]; Find All returns top-level.results[]. Result-bearing commands includesource,citation, andchunk_idwhen available. Use those fields as the citation trail, then callread-passageswhen you need exact surrounding text. possible_conflict: truemeans top hits span multiple similarly scored documents; inspect the relevant sources before answering.ingest-status,read-document, and entity commands may require a Full-tier API key. If access is denied, continue with search and passage reads, and tell the user the key may be scoped too narrowly for that command.- The CLI exits non-zero on failure. Exit code 3 specifically means an admin has disabled CLI access; tell the user.
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.
- 12d ago First seen · 25 lines · 42 tokens per session scan A 9dc489cce37c
harbor-clerk is a skill published in the GitHub repository r0shi/harborclerk (2 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 450 once invoked, about $0.0002 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
tencent-docs
A skill for creating, reading, editing, searching, and managing Tencent Docs, an online document and spreadsheet service.
government-writing
A skill for writing formal Chinese government documents, including notices and opinions, in the required official format.
ima-skills
Tencent IMA OpenAPI skill for notes and knowledge-base operations. Use after the user connects IMA in Pinvou Plugin Center.
lark-base
A guide for managing Lark Base, Feishu's spreadsheet-like database and workspace tool. It covers tables, fields, records, views, formulas, forms, dashboards, applications, workflows, and permissions.
visualizer
A skill for turning structured data, spreadsheets, and business metrics into HTML charts and dashboards using Chart.js, a JavaScript charting library.
lark-doc
A tool for working with documents, wikis, images, attachments, whiteboards, and notes in Feishu, also called Lark. It supports reading, creating, editing, exporting, and restoring document content.