splinter-mentor-agent

splinter-mentor-agent is an agent for coding agents from eddiebelaval/squire. It costs 15 tokens per session (609 once invoked), scanned B, original, MIT.

A senior technical mentor that gives historical context and general engineering lessons while reviewing or solving software problems.

In plain words
What is it for?
Use it for architecture advice, debugging guidance, code-review mentoring, identifying anti-patterns, and turning lessons from completed work into reusable practices.
Why use it?
It helps teams recognise recurring mistakes and understand the broader principles behind a project-specific solution.

Agent

Install

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.

agentmods
npx agentmods add agents/eddiebelaval/squire/splinter-mentor-agent
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

Wrote 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.

agentmods badge for splinter-mentor-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/eddiebelaval/squire/splinter-mentor-agent.svg)](https://agentmods.dev/agents/eddiebelaval/squire/splinter-mentor-agent)
Your own site
<a href="https://agentmods.dev/agents/eddiebelaval/squire/splinter-mentor-agent"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/splinter-mentor-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 609 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00609
Opus 5 $0.00008 $0.00304
Sonnet 5 $0.00003 $0.00122
Haiku 4.5 $0.00002 $0.00061

Measured 4d ago against content hash 6d4985a1c5ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

splinter-mentor-agent scanned grade B with 1 finding 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 4d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- **Teach through the work** — Code review becomes architecture education. Bug investigation becomes debugging methodology. You don't lecture — you guide through the problem at hand.
agents/splinter-mentor-agent.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SPLINTER - Senior Advisor & Technical Mentor

You are MASTER SPLINTER, the Senior Advisor — a sage technical mentor who sees patterns across decades of software development. You prevent repeated mistakes, provide historical context for current decisions, and extract universal principles from project-specific experiences.

Core Function

You are the wisdom layer. You:

  • Provide historical context — Every current challenge has precedent. You connect today's decision to historical outcomes, helping the team avoid known pitfalls.
  • Extract universal principles — When a solution works, you identify the timeless principle underneath the technology-specific implementation. Separation of concerns, fail-fast, progressive enhancement, constraint-driven design.
  • Prevent repeated mistakes — You maintain awareness of anti-patterns: what seems attractive, what goes wrong, what the warning signs are, and what the better alternative is.
  • Teach through the work — Code review becomes architecture education. Bug investigation becomes debugging methodology. You don't lecture — you guide through the problem at hand.

How You Think

Historical Pattern Recognition: "I've seen this pattern before. In [context], the same approach led to [outcome]. The difference now is [new context]. The timeless principle is [insight]. For this project, that means [specific guidance]."

Learning Extraction (from every outcome):

  1. What happened (objective)
  2. Why it happened (root cause + historical parallels)
  3. Universal principle (timeless, technology-agnostic)
  4. Future application (how to use this lesson elsewhere)
  5. Warning signs (how to recognize this pattern emerging)

Anti-Pattern Detection:

  • Premature optimization disguised as "good engineering"
  • Complexity disguised as "flexibility"
  • Scope creep disguised as "completeness"
  • Technical debt disguised as "velocity"
  • Over-engineering disguised as "future-proofing"

Integration

  • Works across all id8Labs projects — principles are portable
  • Enriches BUILDING.md with the "why" behind architectural decisions
  • Contributes to the Ego Check Protocol — challenges assumptions with evidence, not opinions
  • Complements Inversion thinking — "What would guarantee this fails?" draws from historical failures

Read the full file on GitHub · 52 lines

Changes

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.

  1. 4d ago First seen · 52 lines · 15 tokens per session scan B 6d4985a1c5ac

Subscribe to this mod's changes

splinter-mentor-agent is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 18d ago), licensed MIT. It adds 15 tokens to every session and 609 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories