substrate-pruner

substrate-pruner is an agent for coding agents from nestharus/agent-implementation-skill. It costs 45 tokens per session (967 once invoked), scanned A, original, MIT.

A project-integration agent that compares findings from multiple project sections and reduces them to a small set of shared decisions. It looks for repeated needs, contradictions, and decisions that can wait.

In plain words
What is it for?
Use it to build a dependency graph, resolve shared integration points, and produce anchor decisions and a seed plan.
Why use it?
It prevents separate sections from choosing incompatible interfaces or duplicating the same shared work.

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/nestharus/agent-implementation-skill/substrate-pruner
Clone the repo
git clone --depth 1 https://github.com/nestharus/agent-implementation-skill

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 substrate-pruner

README.md
[![agentmods](https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/substrate-pruner.svg)](https://agentmods.dev/agents/nestharus/agent-implementation-skill/substrate-pruner)
Your own site
<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>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 967 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00045 $0.00967
Opus 5 $0.00023 $0.00483
Sonnet 5 $0.00009 $0.00193
Haiku 4.5 $0.00005 $0.00097

Measured yesterday against content hash 550c5757978e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

src/scan/agents/substrate-pruner.md · 121 lines

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:

  1. Build a dependency graph from all shards
  2. Identify convergence patterns (same need from multiple sections)
  3. Identify contradictions (competing designs for the same seam)
  4. For each shared seam: is it FORCED (must decide now) or DEFERRABLE?
  5. 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

  1. All shard JSON files — the complete set of section shards
  2. Global proposal/alignment — the overarching project intent
  3. Codemap — project understanding (for brownfield context)
  4. 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)

Read the full file on GitHub · 121 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. yesterday First seen · 121 lines · 45 tokens per session scan A 550c5757978e

Subscribe to this mod's changes

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.