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 usefulmove/enso --skill document-knowledge-basegit clone --depth 1 https://github.com/usefulmove/ensoWrote 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/usefulmove/enso/document-knowledge-base)<a href="https://agentmods.dev/skills/usefulmove/enso/document-knowledge-base"><img src="https://agentmods.dev/badge/skills/usefulmove/enso/document-knowledge-base/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/usefulmove/enso/document-knowledge-base"><img src="https://agentmods.dev/badge/skills/usefulmove/enso/document-knowledge-base.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 | $0.00054 | $0.02529 |
| Opus 5.5 | $0.00022 | $0.01012 |
| Sonnet 5.5 | $0.00011 | $0.00506 |
| Haiku 4.5 | $0.00005 | $0.00253 |
Grade A, and why
document-knowledge-base 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 1mo 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Load this skill when:
- Asked to create or update a knowledge base
- Documenting a codebase, system, API, domain, or process for the first time
- Refreshing a KB entry that may be stale
- Bootstrapping a
docs/core/architecture/structure in a new project
The Core Idea
A knowledge base is not a library. It's a web.
Coverage is not the goal. The value is in the connections between entries — the relationships that let an agent (or a human) navigate from what they know to what they need. An entry with five accurate cross-references is worth more than a comprehensive entry with none.
Core Concepts
Entry Lifecycle
Every KB entry has a status:
| Status | Meaning |
|---|---|
stub |
Node is known to exist; not yet documented |
draft |
Documented from discovery; not yet verified against source |
verified |
Confirmed accurate against source |
stale |
Previously accurate; source has changed |
Recommended Frontmatter
Keep frontmatter minimal. These fields matter for KB health:
---
title: <human-readable name>
source: <path, URL, or concept identifier — whatever was probed>
status: stub | draft | verified | stale
related: [<other entry paths or titles>]
last_updated: <YYYY-MM-DD>
---
Add domain-specific fields as needed (e.g., tags, owner, version). Don't over-engineer frontmatter for a first pass — status and last_updated are the minimum viable fields.
Naming for Navigability
KB entries and files are discovered by name before their content is read. Names should be self-describing.
Entry names (titles and filenames):
- Use the subject's actual name, not a generic label:
websocket-communicationnotlayer-3 - Prefer noun phrases that match how the subject is referred to in the codebase or domain
- Avoid abbreviations unless they're universally understood in context
- Directory names should match the entry title in kebab-case:
websocket-communication/README.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.
- 1mo ago First seen · 327 lines · 54 tokens per session scan A b0e03fe2b75b
document-knowledge-base is a skill published in the GitHub repository usefulmove/enso (2 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 2,529 once invoked, about $0.0002 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
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
capabilities
Your capability catalog — read this at boot. Lists the temporal date-range skills and the external integrations (reached via the loopback broker) available to you as a spawned worker, and exactly how to call each. Read-only. Consult it whenever you're unsure what tools/integrations you have or how to invoke them.
temporal
Resolve ANY named time window — today, yesterday, thisWeek, lastWeek, last7Days, last30Days, last90Days, thisMonth, lastMonth, thisQuarter, lastQuarter, thisYear, lastYear, last12Months — or an arbitrary range (lastNdays / lastNweeks / lastNmonths) to a concrete ISO date range relative to your run time. Read-only: no…
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
thisQuarter
Resolve "thisQuarter" to a concrete ISO date range relative to your run time — this quarter so far (quarter start → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a quarter-to-date task (QTD…