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 eliransu/digital-brain --skill wiki-prunegit clone --depth 1 https://github.com/eliransu/digital-brainWrote 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/eliransu/digital-brain/wiki-prune)<a href="https://agentmods.dev/skills/eliransu/digital-brain/wiki-prune"><img src="https://agentmods.dev/badge/skills/eliransu/digital-brain/wiki-prune/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/eliransu/digital-brain/wiki-prune"><img src="https://agentmods.dev/badge/skills/eliransu/digital-brain/wiki-prune.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 | $0.00124 | $0.01939 |
| Opus 5 | $0.00062 | $0.00970 |
| Sonnet 5 | $0.00025 | $0.00388 |
| Haiku 4.5 | $0.00012 | $0.00194 |
Grade C, and why
wiki-prune scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- On `y`, `rm -rf` them. On anything else, abort. How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-prune: Weekly Daily-Folder Janitor
/digital-brain:sync writes a folder per day under wiki/daily/. Left alone, those pile up forever and /sup slows down. wiki-prune is the janitor: every Monday it archives folders older than 7 days into a per-ISO-week directory under wiki/.archive/, so the live wiki/daily/ directory only ever holds the current week.
Rules of engagement:
- Dry run by default. Print what would happen. Move nothing until
--commit. - Archive, don't delete. Move folders into
wiki/.archive/YYYY-WW/, preserving structure. Originals stay recoverable viamvback. - Hard delete only on explicit opt-in. With
--hard, delete archive entries older than 30 days from the archive root. Use sparingly. - Fold before prune (recommended). If
wiki-foldhasn't run in the last 7 days, warn before pruning so context isn't lost. - Never touch the live week. Anything dated within the last
retentiondays stays in place. - Skip non-date folders. Only
YYYY-MM-DD/entries are candidates._config.jsonand anything else is left alone.
Inputs / flags
| Flag | Effect |
|---|---|
| (none) | Dry run. List candidates, suggest next run. No filesystem changes. |
--commit |
Move matching folders into wiki/.archive/YYYY-WW/. |
--hard |
After archiving, delete archive entries older than 30 days. Requires Y/N in chat. |
--retention=N |
Override the 7-day window. Rare — default is 7. |
--skip-fold-check |
Don't warn about stale wiki-fold. |
Workflow
- Compute cutoff.
today = date +%Y-%m-%d(local time).cutoff = today - retention(default 7 days). Anything strictly older than the cutoff is a candidate.
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 First seen · 160 lines · 124 tokens per session scan C c0fbcaab0afc
wiki-prune is a skill published in the GitHub repository eliransu/digital-brain (1 stars, last pushed 3mo ago), licensed MIT. It adds 124 tokens to every session and 1,939 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
obsidian-cli
Obsidian vault integration via official CLI. Use when: capturing dev artifacts to Obsidian vault, searching vault for context, appending to daily note, managing tasks in vault. Not for: general note-taking without Obsidian (use regular files), browsing Obsidian docs (use agent-browser). Output: vault search results…
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
anyr
Use when reading, searching, creating, or updating Anytype documents (objects, spaces, types, properties, files, chats) from the command line with the configured anyr CLI, including JSON output patterns for scripting.
lov-kb-organize
A knowledge-base maintenance tool that checks documents, images, indexes, and internal links. It can find duplicates and organize files without automatically merging uncertain matches.
migrate
Scan the project and migrate existing documentation into OKF format. Use when the user wants to populate the knowledge base from existing docs, README, schemas, API specs, runbooks, or any structured project knowledge. Trigger on "migrate to okf", "populate the knowledge base", "scan my docs", "convert docs to okf"…
reduce
Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract…