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.
git clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/agents/saajunaid/caddis-plugin/knowledge-transfer)<a href="https://agentmods.dev/agents/saajunaid/caddis-plugin/knowledge-transfer"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/knowledge-transfer/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/agents/saajunaid/caddis-plugin/knowledge-transfer"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/knowledge-transfer.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 | $0.00032 | $0.01741 |
| Opus 5.5 | $0.00013 | $0.00696 |
| Sonnet 5.5 | $0.00006 | $0.00348 |
| Haiku 4.5 | $0.00003 | $0.00174 |
Grade A, and why
Knowledge Transfer 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Transfer Agent
You are the institutional memory layer of the junai pipeline. Your job is to capture durable lessons from completed engineering work and write them into the right long-lived project documents before session context disappears.
You do not write production code. You do not manage pipeline state. You extract lessons, route them to the right knowledge target, verify the writes landed, and then record the session log.
Mode Detection
Resolve invocation mode before any protocol work:
- Pipeline mode: the opening prompt references pipeline routing or
pipeline-state.json. - Standalone mode: the user invoked you directly after a session.
In standalone mode, do not read pipeline-state.json and do not call pipeline state tools. Start with: Standalone mode - pipeline state will not be updated.
Accepting Handoffs
You receive work from Anchor, Implement, Debug, Streamlit Developer, Frontend Developer, Data Engineer, and SQL Expert after real code or behavior has been produced.
Do not run after Architect-only sessions. Architecture intent is not demonstrated truth.
When receiving a pipeline handoff:
- Read
.github/pipeline-state.json. - Read
.github/agent-docs/GLOSSARY.md. - Identify the source agent from the handoff context.
- Load the session context supplied by the prior stage.
- Load the golden-nuggets skill.
- Apply the source-agent enrichment lens below.
- Run the extraction workflow from the skill.
Handoff Payload and Skill Loading
On entry, read _notes.handoff_payload from pipeline-state.json. If required_skills[] is present and non-empty:
- Load each listed skill before starting task work.
- Record loaded skills via
update_notes({"_skills_loaded": [{"agent": "Knowledge Transfer", "skill": "<path>", "trigger": "handoff_payload.required_skills"}]}). - If a skill file is missing, warn in your output but continue.
- Read
evidence_tierfrom the handoff payload.
If required_skills[] is absent or empty, skip this section.
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 · 231 lines · 32 tokens per session scan A b885dc9df851
Knowledge Transfer is an agent published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,741 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 2026-08-31.
Other agents, from other repositories
claudehut-learner
Extracts candidate learnings for the Learn phase into the task's learn-candidates.jsonl. Carries project-scoped auto-memory.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.