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/panaversity/agentfactory-business-plugins/context-loadernpx skills add panaversity/agentfactory-business-plugins --skill context-loadergit clone --depth 1 https://github.com/panaversity/agentfactory-business-pluginsWrote 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/panaversity/agentfactory-business-plugins/context-loader)<a href="https://agentmods.dev/skills/panaversity/agentfactory-business-plugins/context-loader"><img src="https://agentmods.dev/badge/skills/panaversity/agentfactory-business-plugins/context-loader.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 | $0.00084 | $0.00695 |
| Opus 5 | $0.00042 | $0.00347 |
| Sonnet 5 | $0.00017 | $0.00139 |
| Haiku 4.5 | $0.00008 | $0.00069 |
Grade A, and why
context-loader 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 5d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CONTEXT INJECTION WORKFLOW
STEP 1 — LOAD CONTEXT
Read work.local.md in the current working directory.
If it does not exist, tell the user to run /agentic-office:setup first.
Check agent_integrations in work.local.md for configured domain agents.
STEP 2 — IDENTIFY CONTEXT TYPE
TYPE 1: SINGLE-DOMAIN CONTEXT Load context from one domain for a specific endeavour. Example: "Load finance context before I review the analytics budget proposal"
TYPE 2: CROSS-DOMAIN CONTEXT Load context from multiple domains simultaneously. Example: "Load HR + Finance + Ops context for onboarding Dr. Sana Mirza"
TYPE 3: PERSON CONTEXT Load everything known about a specific person before an interaction. Example: "Load full context on Omar before our budget conversation"
TYPE 4: PROJECT CONTEXT Load full project context including cross-domain implications. Example: "Load full context on Project Nighthawk"
TYPE 5: DECISION CONTEXT Load context needed to make a specific decision well. Example: "Load context for the Islamabad expansion decision"
STEP 3 — PRODUCE OUTPUT
OUTPUT STRUCTURE:
CONTEXT BRIEF — [Subject]
Loaded from: [Domain(s) + work.local.md layers used]
================================================================
CORE CONTEXT:
[The most important things to know for this endeavour]
[DOMAIN 1] CONTEXT:
[What is known from this domain that is relevant]
[Current status; recent changes; open items]
[DOMAIN 2] CONTEXT:
[Same structure]
PEOPLE CONTEXT:
[Anyone involved — communication style; current focus; approach tips]
WHAT TO WATCH FOR:
[Specific things to pay attention to given the full context]
GAPS IN CONTEXT:
[What is NOT known that would be useful — and how to get it]
================================================================
Integration Protocol
When loading cross-domain context, check each configured domain:
HR domain: Check: Is anyone involved in a new hire / onboarding / performance situation? Check: Any HR obligations or approvals affecting this endeavour?
What ships with it
2 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.
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.
- 5d ago First seen · 103 lines · 84 tokens per session scan A 5c8044c3a98f
context-loader is a skill published in the GitHub repository panaversity/agentfactory-business-plugins (28 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 695 once invoked, about $0.0004 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
remember
Recall what was actually said or decided earlier — across daily summaries, the conversation buffer, files people sent, live sessions and scheduled runs. Use whenever someone refers to prior context ("what did we decide", "last time", "as I said", "the file I sent you", "what did you tell me"), or for any synonym of…
memory-read
Query-first indexing and retrieval for Operator OS memory. Use when asked to find prior context, search memory, rebuild the memory index, or answer from the workspace without loading large files by default.
memory-manage
Manage Active updates, atomic session handoffs, and human-gated Long-Term proposals. Use when asked to remember something, preserve a decision, log meaningful work, or review memory.
brain-sync
Sync knowledge and learnings to the shared appie-brain repo. Every Appie commits with their own identity so contributions are traceable. Use after: complex tasks (5+ tool calls), significant discoveries, new skills, or client work. Fleet: Appie-1 (Orchestrator/MacMini), Appie-2 (CMO/DO), Appie-3 (CTO/VPS).
project-context-sync
Keep a living project state document updated after each commit, so any agent (or future session) can instantly understand where things stand.
memory-search
Search and retrieve information from the Appie brain — daily logs, project notes, decisions, topics, and long-term memory files stored in /.hermes/memory/. Use this skill whenever you need to recall past conversations, decisions, project context, personal preferences, or anything discussed previously.