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/hraness/kb/kbnpx skills add hraness/kb --skill kbgit clone --depth 1 https://github.com/hraness/kbWhat 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 | $0.00133 | $0.01053 |
| Opus 5 | $0.00067 | $0.00526 |
| Sonnet 5 | $0.00027 | $0.00211 |
| Haiku 4.5 | $0.00013 | $0.00105 |
Grade A, and why
kb 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 2d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work with KB
Use hraness/kb to preserve and retrieve inspectable agent memory in Markdown and Git. Select the smallest workflow that matches the request, then load only its references.
Prepare the runtime
Use an existing kb command when one is available. Do not reinstall or upgrade
it merely because this skill loaded.
If kb is missing, check for Bun. Bun is the required runtime. When Bun is
also missing, install it with the official instructions at
https://bun.sh/docs/installation under the environment's normal approval
rules, then repeat command discovery. Install KB only while kb remains
missing:
command -v kb >/dev/null 2>&1 || {
command -v bun >/dev/null 2>&1 || exit 1
bun add --global @hraness/[email protected]
}
kb --help
The exact npm version is the immutable release owned by this skill. Do not
replace it with latest, a branch, or an unpinned package source. Both installed
commands require Bun 1.3.14 or newer in PATH. Run kb doctor when the
chosen workflow may need browser capture, media tools, PDF extraction, OCR, or
local semantic search.
Installation ends after command verification. Never run kb init, create a
vault, refresh a catalog, or edit Markdown as an installation side effect.
Initialize or mutate a vault only when the user's request requires that change.
Route the request
| User intent | Read |
|---|---|
| Find notes, search one vault or an authorized portfolio, load repository-path context, inspect plans or decisions, follow backlinks or relationships, audit vault organization, or retrieve Git provenance | Query the knowledge base |
| Save, clip, scrape, or archive a URL, article, social post or thread, GitHub or Discourse discussion, signed-in page, feed, inbox, private document, WhatsApp conversation, or YouTube page | Capture web content; add browser authentication for signed-in sources and platform routing when route choice or completeness matters |
| Import, extract, archive, OCR, or convert a local or public PDF into Markdown | Save a PDF; add PDF image review for scans, screenshots, conversations, charts, or mixed media |
| Create or update an implementation plan, proposal, RFC, migration plan, execution audit, or phased checklist in the vault | Write a durable plan and use its structure |
| Review recurring ideas, promote concepts, or add and verify typed relationships | Percolate concepts and relationships |
| Refresh or validate the catalog, graph, attachments, repository scopes, context mappings, or overall vault health | Refresh and check the knowledge base |
What ships with it
12 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.
- AGENTS.md 2.1 KB
- agents/openai.yaml 240 B
- references/pdf-review.md 2.2 KB
- references/percolate.md 5.0 KB
- references/plan-structure.md 2.6 KB
- references/plan.md 5.5 KB
- references/query.md 13 KB
- references/refresh.md 6.0 KB
- references/save-pdf.md 4.7 KB
- references/save-url.md 11 KB
- references/url-authentication.md 4.3 KB
- references/url-platforms.md 4.6 KB
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.
- 2d ago First seen · 83 lines · 133 tokens per session scan A 75d9ee17e916
kb is a skill published in the GitHub repository hraness/kb (13 stars, last pushed 2d ago), licensed MIT. It adds 133 tokens to every session and 1,053 once invoked, about $0.0007 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
my-wiki
Manage local OKF-compatible Markdown My Wiki vaults with an AI agent. Use for capturing webpages, PDFs, Office documents, notes, images, folders, and ZIP bundles as References; maintaining Reference-to-Concept evidence links; searching or answering from a vault; checking or repairing vault health; switching among…
binder-modeling
Binder data modeling — define entity types, fields, relations, constraints, views, and navigation. Use when asked to "create a type", "add a field", "define a schema", "set up relations", "model entities", "create a view", "set up navigation", "render entities as files", or design a binder workspace schema.
binder-app
Build a small HTTP app (dashboard, kanban board, admin panel, custom UI) on top of an existing Binder workspace. Use when asked to "create an app", "build a dashboard", "show records in a chart", "make a kanban/board", "build an admin panel", or "add a UI on top of binder".
binder-import
Import external data into a Binder workspace. Handles CSV, JSON, YAML, Markdown files, and directories of Markdown. Use when asked to "import data", "load records from a file", "ingest documents", "migrate data into binder", or bulk-create records from an external source.
binder-cli
Binder CLI for knowledge graph operations — CRUD, search, schema inspection, transaction import, docs rendering. Use when asked to "query binder", "search records", "create a record", "check the schema", "import transactions", "undo changes", or work with a binder workspace.
capture-task
Capture a new task — create a draft or pending Task record from a rough idea or detailed spec. Use when asked to "add a task", "log a bug", "create a task", or "add to backlog".