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/cobibean/agent-memory-wiki/wikijanitornpx skills add cobibean/agent-memory-wiki --skill wikijanitorgit clone --depth 1 https://github.com/cobibean/agent-memory-wikiWrote 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/cobibean/agent-memory-wiki/wikijanitor)<a href="https://agentmods.dev/skills/cobibean/agent-memory-wiki/wikijanitor"><img src="https://agentmods.dev/badge/skills/cobibean/agent-memory-wiki/wikijanitor.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00480 |
| Opus 5 | $0.00018 | $0.00240 |
| Sonnet 5 | $0.00007 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
wikijanitor 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 6d 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
Wiki Janitor — Compatibility Alias
This skill keeps /wikijanitor and older references working. The canonical package is obsidian-memory-wiki.
Load and follow obsidian-memory-wiki, then execute its Wiki Janitor Maintenance phase. New cron wrappers should invoke:
--skills obsidian-memory-wiki
Do not schedule new runs with the retired split dependency --skills wikijanitor,obsidian.
If the parent skill is unavailable, use this fallback:
- Review the requested lookback window, defaulting to 24 hours.
- Compare recent sessions with Daily Logs, Session Logs, and Janitor Reports.
- If there is no activity, or only routine reconciliation with no user attention needed, make no user notification.
- If there is activity, write a Janitor Report under
Janitor Reports/. - Make only conservative routine changes such as backlinks or index links.
- Record uncertainty and missing notes as gaps instead of inventing narrative.
- Keep user-facing output concise and never print secrets.
- Scheduled wrappers validate an internal digest only between exact marker lines:
[[WIKI_JANITOR_NOTIFY]]
<concise internal digest>
[[WIKI_JANITOR_END]]
Use exactly [[WIKI_JANITOR_SILENT]] for a no-activity or routine-only run. Notify only for warnings, gaps, uncertainty, or actions requiring user attention. The wrapper must emit a constant notification and never forward model-authored digest text. Unmarked or partially marked raw output must remain suppressed.
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.
- 6d ago First seen · 47 lines · 37 tokens per session scan A f780330dcaf1
wikijanitor is a skill published in the GitHub repository cobibean/agent-memory-wiki (23 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 480 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 2026-08-30.
Other skills, from other repositories
personal-api
Turn an Obsidian vault into an AI-readable personal identity layer. Use when setting up ME.md and AGENT.md, scaffolding the full Knowledge Palace v2 structure, onboarding AI assistants, or maintaining the vault contract. Default setup creates the complete 30.knowledge system; --minimal creates only the lightweight…
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…
rethink
Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".
graph
Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".
remember
Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".
seed
Add a source file to the processing queue. Checks for duplicates, creates archive folder, moves source from inbox, creates extract task, and updates queue. Triggers on "/seed", "/seed [file]", "queue this for processing".