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 Tx1207/hello-scholar --skill docs-maintenancegit clone --depth 1 https://github.com/Tx1207/hello-scholarWrote 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/tx1207/hello-scholar/docs-maintenance)<a href="https://agentmods.dev/skills/tx1207/hello-scholar/docs-maintenance"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/docs-maintenance/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/tx1207/hello-scholar/docs-maintenance"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/docs-maintenance.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 | $0.00029 | $0.00706 |
| Opus 5.5 | $0.00012 | $0.00282 |
| Sonnet 5.5 | $0.00006 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
docs-maintenance 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 9d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Maintenance
Keep project knowledge consistent with what it claims to describe. A reader should be able to distinguish the adopted system, proposed changes, actual execution evidence, and navigation without reconciling conflicting copies.
Identify the fact and its owner
Start from the requested document or the facts changed by implementation. Ask what would mislead a reader if left unchanged, then follow the relevant references. A moved artifact may require a path correction; a changed module responsibility may require an Architecture update. The number of edited files or a new commit alone does not establish either need.
Use the owning source for each claim: a Spec holds intended design and judgment criteria, a Record holds one execution's facts, Architecture holds implemented and adopted structure, and an Index locates those sources. If code and a draft Spec differ, first determine whether the design is still pending; do not resolve that difference by pretending the proposal was adopted. For a partially implemented Spec, state only the verified and adopted portion as current architecture.
Explain important ownership, dependency, and runtime relationships in the document itself. Cite code and evidence so readers can verify them. Avoid replacing useful explanation with a file inventory, copying the same fact into several owners, or promoting generated navigation into authority.
Operations
Modes may be combined in a sensible order when the user's authorization already covers them. Choose the operation that repairs the actual knowledge gap:
- Check: run
hello-scholar docs checkand report its exit code, errors, notices, and relative paths. This operation is strictly read-only: do not sync or repair anything. - Sync: run
hello-scholar docs sync. The CLI alone may update global, Topic, and RunINDEX.mdfiles. On failure, report diagnostics and do not hand-rebuild an Index. - Architecture: update
hello-scholar/architecture.mdfrom verified implemented and adopted facts when the user requests it or the authorized implementation materially changes structure, module ownership, runtime flow, public contracts, or persistent locations. Read assets/architecture-template.md for English or assets/architecture-template.zh_CN.md for Chinese. Preserve unaffected content, exclude future designs and unadopted experiments, and describe unresolved facts explicitly. A missing Architecture notice alone does not authorize reconstructing or adopting one. - Recover: check first, then sync when source documents parse. Inventory orphaned or legacy material and reconstruct a reviewable Architecture draft from code, Git, completed acceptance evidence, and valid Records. Do not guess through parse failures or write a formal Architecture unless the request authorizes that write.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago Changed · +12 lines 4733c7136e1b
- 1mo ago Changed · -58 lines · -13 tokens per session 10add257a7b9
- 2mo ago First seen · 78 lines · 42 tokens per session scan A a13ee2c46569
docs-maintenance is a skill published in the GitHub repository Tx1207/hello-scholar (10 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 706 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.