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/agno-agi/context/knowledge-reviewnpx skills add agno-agi/context --skill knowledge-reviewgit clone --depth 1 https://github.com/agno-agi/contextWrote 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/agno-agi/context/knowledge-review)<a href="https://agentmods.dev/skills/agno-agi/context/knowledge-review"><img src="https://agentmods.dev/badge/skills/agno-agi/context/knowledge-review.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 | $0.00103 | $0.01041 |
| Opus 5 | $0.00051 | $0.00521 |
| Sonnet 5 | $0.00021 | $0.00208 |
| Haiku 4.5 | $0.00010 | $0.00104 |
Grade A, and why
knowledge-review 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 4d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Review
Runtime skill — a playbook the deployed @context agent runs for its owner, invoked in natural language. Not a coding-agent workflow; those live in
.agents/skills/.
Sweep the knowledge base and report what needs attention so nothing rots. This is read-only: it surfaces issues and suggests the fix, it never edits, files, or deletes anything itself. The owner decides what to act on.
The knowledge base searches by keyword and the index (no search-by-meaning), so this sweep works the same way: list the tree, read the index, and reconcile the two.
Procedure
- Get the lay of the land. Two
query_knowledgereads up front:- Ask it to list every file and folder, recursively — the raw tree, not a summary.
- Ask it for the root
README.mdindex table, verbatim — every spec and page it lists. Hold both so you can reconcile what's on disk against what the index claims.
- Reconcile disk against the index.
- Orphaned — a folder or page on disk that the index never lists. It's unfindable through the front door.
- Index drift — a row in the index pointing at a folder or page that doesn't exist on disk. A dead link.
- Spot-check the suspect pages with targeted
query_knowledgereads:- Stubs — a page that's a heading and a line or two of placeholder ("stub page", "no details yet", a single sentence) with no real substance.
- Stale specs — a spec whose status table still says draft / in progress / for review, or whose own "last updated" line is well in the past, with no sign it has moved. Flag it as worth a look, don't assume it's dead.
- Missing decision log — a spec with a design or implementation but no
decisions.md(or an empty one). Decisions got made; they were never written down. - Dead cross-links (when you notice them) — a link from one page to another path that isn't there.
- Write the "what needs attention" list. Group the findings, most actionable first. Each line: the path, one sentence on why it needs attention, and the suggested next step (add it to the index, flesh out the stub, write the ADR, fix the index row). Suggest only; don't do it.
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.
- 4d ago First seen · 74 lines · 103 tokens per session scan A 0129e7cf1630
knowledge-review is a skill published in the GitHub repository agno-agi/context (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,041 once invoked, about $0.0005 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
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
knowledge_base
Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.
openlore
Query and publish to an OpenLore knowledge base over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.
openlore-housekeeping
Audit and maintain a shared OpenLore knowledge base. Use on a schedule or on request to find stale docs, broken links, unreviewed inbox items, and missing skill coverage, then publish an audit report.
qi-cli
Guide for using qi, a local knowledge search CLI for macOS and Linux. Use this skill whenever the user asks about qi commands, indexing documents, searching a knowledge base, configuring providers (Ollama, OpenAI), understanding search modes (BM25, hybrid, vector), or anything related to the qi tool. Triggers on…
knowledge
Search and author KNOWLEDGE.md background-knowledge documents - frontmatter schema, search/check scripts, and the generated/verified lifecycle rules.