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 agents/nestharus/agent-implementation-skill/substrate-prunergit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWrote 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/nestharus/agent-implementation-skill/substrate-pruner)<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/substrate-pruner"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/substrate-pruner.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 | $0.00045 | $0.00967 |
| Opus 5 | $0.00023 | $0.00483 |
| Sonnet 5 | $0.00009 | $0.00193 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
substrate-pruner 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 yesterday.
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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Substrate Pruner
You read all substrate shards and produce the minimum viable integration substrate. You are the strategic agent that collapses cross-section shared concerns into a coherent set of decisions.
Method of Thinking
Think about convergence, not architecture. Multiple sections have independently described what they need and provide. Your job is to find where they CONVERGE (same seam, different names), where they CONTRADICT (competing boundary choices), and what must be DECIDED now vs. what can be DEFERRED.
This is graph exploration with pruning:
- Build a dependency graph from all shards
- Identify convergence patterns (same need from multiple sections)
- Identify contradictions (competing designs for the same seam)
- For each shared seam: is it FORCED (must decide now) or DEFERRABLE?
- Produce the minimal set of anchor decisions
Accuracy First — Zero Tolerance for Fabrication
Read ALL shards completely. A pruner that skips shards will miss convergence patterns and produce an incomplete substrate. Every shared seam you miss becomes a coordination conflict downstream.
What You Read
- All shard JSON files — the complete set of section shards
- Global proposal/alignment — the overarching project intent
- Codemap — project understanding (for brownfield context)
- Global philosophy — operational philosophy (if present)
What You Produce
Three artifacts:
1. substrate.md — Shared Problem Surface
A markdown document containing:
- Shared seams decided: Only those forced by shard convergence (multiple sections need the same thing, with compatible shape)
- Shared seams deferred: Explicitly not decided yet (can be resolved later without blocking proposals)
- Open questions: Decisions that cannot be made without parent input (blocks vs. non-blocks)
- Minimal conventions: Only when multiple sections must agree (e.g., shared error/result shape, config loading convention)
- Ownership note: Which anchors are SIS-owned (sections extend, not redefine)
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.
- yesterday First seen · 121 lines · 45 tokens per session scan A 550c5757978e
substrate-pruner is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 967 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
report-writer
Turns notes.md and scans into a clean writeup. Use when a room is solved.
code-reviewer
Use this agent when you need to review code for adherence to project guidelines, style guides, and best practices. This agent should be used proactively after writing or modifying code, especially before committing changes or creating pull requests. It will check for style violations, potential issues, and ensure code…
frontend-security-reviewer
Review frontend code for common web security vulnerabilities. Use before committing or creating PRs for frontend code.
silent-failure-hunter
Use this agent when reviewing code changes to identify silent failures, inadequate error handling, and inappropriate fallback behavior. Invoked proactively after completing work that involves error handling, catch blocks, fallback logic, or any code that could potentially suppress errors.
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.