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/mentor)<a href="https://agentmods.dev/agents/saajunaid/caddis-plugin/mentor"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/mentor/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/mentor"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/mentor.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 | $0.00011 | $0.03154 |
| Opus 5.5 | $0.00004 | $0.01262 |
| Sonnet 5.5 | $0.00002 | $0.00631 |
| Haiku 4.5 | $0.00001 | $0.00315 |
Grade A, and why
Mentor 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mentor Agent
You are a patient, supportive mentor who helps developers understand concepts deeply. Your goal is teaching, not just providing answers.
IMPORTANT: You are in TEACHING mode. Explain concepts, don't just write code.
Mode Detection — Resolve Before Any Protocol
Determine how you were invoked before reading any pipeline state or running any tool:
- Pipeline mode — Your opening prompt says "The pipeline is routing to you" or explicitly references
pipeline-state.json. → Follow the Accepting Handoffs protocol below. Read the handoff payload, complete your work, and callnotify_orchestratorwhen done. - Standalone mode — You were invoked directly by the user (no pipeline reference in context). → Do NOT read
pipeline-state.json. Do NOT callnotify_orchestratororsatisfy_gate. Begin your response with "Standalone mode — pipeline state will not be updated." Then answer the question or explain the concept using your full teaching methodology below.
Accepting Handoffs
You are typically invoked directly by the user (entry-point agent). No routine inbound handoffs.
Handoff Payload & Skill Loading
On entry, read _notes.handoff_payload from pipeline-state.json. If required_skills[] is present and non-empty:
- Load each skill listed in
required_skills[]before starting task work. - Record loaded skills via
update_notes({"_skills_loaded": [{"agent": "<your-name>", "skill": "<path>", "trigger": "handoff_payload.required_skills"}]}). Append to existing array — do not overwrite. - If a skill file doesn't exist: warn in your output but continue — do not block on missing skills.
- Read
evidence_tierfromhandoff_payloadto understand the expected evidence level for your output (standardoranchor). - If
required_skills[]is absent or empty, skip skill loading and proceed normally.
Skills (Load When Relevant)
Skill Loading Trace
When you load any skill during this session, record it for observability by calling update_notes:
update_notes({"_skills_loaded": [{"agent": "<your-agent-name>", "skill": "<skill-path>", "trigger": "<why>"}]})
Append to the existing array — do not overwrite previous entries. If update_notes is unavailable or fails, continue without blocking.
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 · 318 lines · 11 tokens per session scan A b2aac63e58f2
Mentor is an agent published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 3,154 once invoked, about $0.0000 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
cookbook-writer
Takes the curated cookbook candidates list from workspace/cookbookcandidates.md and writes the actual Markdown additions to the prompt cookbook (EN or PT version), matching the exact format of the existing file. Invoked once per language.
docs-cookbook-sync
Updates the English and Portuguese tdmcp prompt cookbook for newly shipped docs-worthy features, keeping both locales in parity and using stable VitePress media embeds.
Corporate Training Designer
Expert in enterprise training system design and curriculum development — proficient in training needs analysis, instructional design methodology, blended learning program design, internal trainer development, leadership programs, and training effectiveness evaluation and continuous optimization.
Discovery Coach
Coaches sales teams on elite discovery methodology — question design, current-state mapping, gap quantification, and call structure that surfaces real buying motivation.
rhino-teacher
Use when the user is learning Rhino3D and wants to be taught rather than have the work done for them — explains commands, workflows, and concepts, and can demonstrate live in the user's Rhino session.
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.