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 adilkalam/orca --skill using-loaded-knowledgegit clone --depth 1 https://github.com/adilkalam/orcaWrote 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/adilkalam/orca/using-loaded-knowledge)<a href="https://agentmods.dev/skills/adilkalam/orca/using-loaded-knowledge"><img src="https://agentmods.dev/badge/skills/adilkalam/orca/using-loaded-knowledge/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/adilkalam/orca/using-loaded-knowledge"><img src="https://agentmods.dev/badge/skills/adilkalam/orca/using-loaded-knowledge.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 | $0.00031 | $0.02289 |
| Opus 5.5 | $0.00012 | $0.00916 |
| Sonnet 5.5 | $0.00006 | $0.00458 |
| Haiku 4.5 | $0.00003 | $0.00229 |
Grade A, and why
using-loaded-knowledge 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YOU MUST FOLLOW THIS CHECKLIST BEFORE EVERY SINGLE RESPONSE.
If you skip this checklist, you WILL make the exact same mistakes that have been made 20+ times before.
Using Loaded Knowledge - MANDATORY Pre-Response Protocol
THE PROBLEM THIS SOLVES
Failure Pattern (costs ~100K tokens per occurrence):
- User asks: "Explain our architecture"
- Claude generates answer WITHOUT checking loaded context
- Claude explains generic system WITHOUT reading actual documentation
- User: "You didn't even read the docs I built"
- Claude: Makes claims about what exists WITHOUT grep verification
- User: Provides evidence showing Claude is completely wrong
- Result: Complete waste of tokens, zero trust, massive frustration
This has happened 20+ times. It MUST stop.
MANDATORY CHECKLIST - BEFORE EVERY RESPONSE
Before responding to ANY user message, you MUST complete ALL steps:
Step 1: Check Auto-Loaded Context Files
These files are ALREADY in your context (loaded via SessionStart hooks):
# Check if question relates to loaded context
ls .orca/orchestration/temp/session-context.md 2>/dev/null
Files to check:
.orca/orchestration/temp/session-context.md- Recent work, decisions, Workshop contextCLAUDE.md- Project instructions, learned rules, workflow guidance- Workshop database - Query via
workshop --workspace .claude/memory <command>
IF your response relates to recent work, systems built, or user preferences → READ these files FIRST
Step 2: System/Documentation Questions
IF user asks about a system, architecture, or anything we built:
# Search /docs for relevant documentation
ls $PROJECT_ROOT/docs/*.md
# Read COMPLETE documentation before explaining
Read $PROJECT_ROOT/docs/[RELEVANT].md
Examples that require /docs reading:
- "Explain our architecture"
- "How does X system work?"
- "What's the Design DNA system?"
- "Tell me about the quality gates"
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 · 355 lines · 31 tokens per session scan A 3569d4aad867
using-loaded-knowledge is a skill published in the GitHub repository adilkalam/orca (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 2,289 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.