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/prep-fornpx skills add agno-agi/context --skill prep-forgit clone --depth 1 https://github.com/agno-agi/contextWhat 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 | $0.00095 | $0.00866 |
| Opus 5 | $0.00048 | $0.00433 |
| Sonnet 5 | $0.00019 | $0.00173 |
| Haiku 4.5 | $0.00010 | $0.00087 |
Grade A, and why
prep-for 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 3d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prep For
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/.
Pull together a tight pre-meeting brief on a subject — a person, company, or project the owner is about to engage. Read-only: gather and synthesize, never file.
Procedure
- Identify the subject. Pin down who/what from the request ("my 3pm with Sarah Lee from Acme" → person Sarah Lee, org Acme). If it's genuinely ambiguous and a wrong guess would waste the brief, ask one clarifying question instead of guessing.
- Sweep what we already know — internal first. Run an entity sweep:
query_crm— contacts, notes, projects, and any reminders/meetings tagged to the subject (name, company, tags, meeting attendees). This is our relationship + history.query_knowledge— knowledge-base prose about the subject (runbooks, summaries, "what I know about X").query_slack(when connected) — recent threads mentioning the subject; the latest exchanges are often the freshest context in the brief.
- Anchor to the meeting. Surface the specific upcoming meeting/reminder with
the subject if there is one — the brief should serve that interaction. When
the
calendarsource is connected, checkquery_calendarfor the real event (time, attendees); whengmailis connected and there's an email thread with the subject, pull the latest exchange withquery_gmail— the most recent thing they said is often the most useful line in the brief. - Widen to the web only for people/orgs we don't know. If the internal
sweep turns up little or nothing on an external person or company (no
contact on file, just a name), call
query_webfor public background — role, current company, recent news. Skip the web when we already have a solid internal picture, and for internal/private topics. Don't pad a brief with generic results, and keep the web query to public identity terms (name + company), not the owner's private notes about them.
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.
- 3d ago First seen · 64 lines · 95 tokens per session scan A d41243cacd7b
prep-for is a skill published in the GitHub repository agno-agi/context (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 95 tokens to every session and 866 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
verification
Prove that a coding task is actually complete. Use this after meaningful code changes, when tests/builds fail or are skipped, before marking a plan or goal complete, and whenever acceptance depends on runtime, security, recovery, performance, or cross-module evidence.
repository-investigation
Investigate an unfamiliar repository before changing it. Use this whenever a coding task spans multiple modules, asks for architecture or root-cause analysis, names behavior whose implementation location is unknown, or risks editing before enough evidence is gathered.
safe-refactoring
Execute behavior-preserving or intentionally scoped refactors safely. Use this for multi-file renames, component/service extraction, state-management changes, API migrations, concurrency refactors, or any request where unrelated user work and subtle contracts must be preserved.
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.
quantmind-dev
Contributor workflow for the QuantMind codebase. Covers contributor setup (environment + hooks), filing issues, commit format, pull request format, and component development across quantmind/ modules (etl, knowledge, configs, preprocess, rag, flows, mind, utils) with tests, examples, and verification. Use when setting…
knowledge_base
Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.