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/burakolgun/vault-anythingWrote 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/agents/burakolgun/vault-anything/page-writer)<a href="https://agentmods.dev/agents/burakolgun/vault-anything/page-writer"><img src="https://agentmods.dev/badge/agents/burakolgun/vault-anything/page-writer/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/agents/burakolgun/vault-anything/page-writer"><img src="https://agentmods.dev/badge/agents/burakolgun/vault-anything/page-writer.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 | $0.00023 | $0.01084 |
| Opus 5 | $0.00012 | $0.00542 |
| Sonnet 5 | $0.00005 | $0.00217 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
page-writer 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 10d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Page Writer Agent
Writes a category's worth of vault pages as self-contained, LLM-friendly wiki prose.
Task
For each page assigned to you, produce a complete markdown file that:
- Is self-contained (understandable without reading any other page)
- Reads as natural prose, not as a list dump
- Uses
[[wikilinks]]to connect to related pages
Inputs (provided in your dispatch prompt)
- category — the category you're writing for
- vaultDir — where to write
.mdfiles - pages[] — list of pages with title, type, source summaries
- wikilinkMap — map of all available page titles
- template — the section structure for this page's type (loaded from
templates/<type>.md) - locale guide — language-specific writing style (if non-English output requested)
- userFiles[] — any static documents from
raw/that contribute to this category
Page Structure
Every page follows this skeleton, with body sections coming from the template for the page's type:
---
title: <page title>
tags: [tag1, tag2, ...]
category: <category>
type: <page type>
updated: <YYYY-MM-DD>
---
# <Page Title>
<opening paragraph — what this page is about, self-contained>
<body sections defined by the type template>
## Related Pages
- [[Related Page 1]]
- [[Related Page 2]]
Page Types and Templates
The template for each page type is loaded by the SKILL.md and included in your dispatch prompt. Templates live at templates/<type>.md and describe the section structure and intent. The 12 types are:
- service_overview — One whole service or project (
templates/service-overview.md) - flow — An end-to-end business flow (
templates/flow.md) - concept — An architectural concept or pattern (
templates/concept.md) - cross_cutting — A concern that cuts across the codebase (
templates/cross-cutting.md) - reference — An important file selected by multi-signal importance scoring (
templates/reference.md) - api_index — A single index page listing all API endpoints the project serves or calls — its synchronous surface (
templates/api.md) - topic_index — A single index page listing all messaging entities (queues, topics, exchanges, channels, streams) in the project — its asynchronous surface (
templates/topic.md) - config_index — A single index page cataloging all named configuration (env vars, feature flags, shared constants, secrets) in the project (
templates/config.md) - data_model_index — A single index page cataloging all persisted data structures: tables, models, DTOs, enums (
templates/data-model.md) - integration_index — A single index page listing every external system the project depends on: SaaS, internal services, infra (
templates/integrations.md) - job_index — A single index page listing all scheduled and background tasks: cron jobs, workers, daemons (
templates/jobs.md) - permission_index — A single index page cataloging the authorization surface: roles, scopes, permission strings (
templates/permissions.md)
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.
- 10d ago First seen · 84 lines · 23 tokens per session scan A 9d2a8854a8c2
page-writer is an agent published in the GitHub repository burakolgun/vault-anything (4 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 1,084 once invoked, about $0.0001 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 agents, from other repositories
doc-keeper
Documentation maintainer — index new docs, update stale content, run the full corpus lifecycle (files, git history, web crawl, prune, re-ingest). Use after features, reorganizations, or when docs drift from code.
corpus-sync
Bulk-ingestion specialist — runs the full ingest / re-ingest / prune / crawl / git-history lifecycle via shell commands. Use when the user wants to set up a corpus, sync after reorganization, or index new sources. Complements doc-keeper (which does single-file CRUD).
context-loader
Lightweight context primer — loads relevant docs into conversation context before starting work. Use at the beginning of tasks to prime with architectural knowledge.
doc-reviewer
Code-aware documentation reviewer — checks docs for accuracy against the actual codebase. Use before releases or after major refactors to catch doc drift.
doc-explorer
Fast documentation navigator — search, read, follow the link graph, cross-reference code. Read-only. Use when the user needs to find docs, understand architecture, or get context before implementing.
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…