speckit.memory-md.capture-from-diff

speckit.memory-md.capture-from-diff is a command for Claude Code from DyanGalih/spec-kit-memory-hub. It costs 13 tokens per session (1,391 once invoked), scanned A, original, MIT.

A command that records lasting technical knowledge and architecture decisions from code differences. A diff is a comparison showing what changed between two versions of files.

In plain words
What is it for?
Examining current or supplied diffs, identifying changed files, and saving durable project knowledge under the configured memory and specification folders.
Why use it?
It helps preserve important decisions instead of leaving them only in a temporary review or conversation. It also checks whether proposed knowledge is confident and not already recorded.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Examining current or supplied diffs, identifying changed files, and saving durable project knowledge under the configured memory and specification folders.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.capture-from-diff
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.

Clone the repo
git clone --depth 1 https://github.com/DyanGalih/spec-kit-memory-hub

Made for: Claude Code.

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 speckit.memory-md.capture-from-diff

README.md
[![agentmods](https://agentmods.dev/badge/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.capture-from-diff.svg)](https://agentmods.dev/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.capture-from-diff)
Your own site
<a href="https://agentmods.dev/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.capture-from-diff"><img src="https://agentmods.dev/badge/commands/dyangalih/spec-kit-memory-hub/speckit.memory-md.capture-from-diff.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,391 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00013 $0.01391
Opus 5 $0.00006 $0.00696
Sonnet 5 $0.00003 $0.00278
Haiku 4.5 $0.00001 $0.00139

Measured 8d ago against content hash a15951c1c175, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

speckit.memory-md.capture-from-diff 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 8d 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.

commands/speckit.memory-md.capture-from-diff.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capture From Diff

You are capturing durable knowledge for memory-hub by analyzing code changes.

Resolve configuration first. Use .specify/extensions/memory-md/config.yml when present; otherwise default to memory_root: docs/memory and specs_root: specs.

Capture is automatic based on your confidence score. Evaluate the proposed durable memory and determine your confidence (0-100%) that it is correct, durable, and non-duplicate. If your confidence is > 50%, automatically approve the capture and register it. If your confidence is <= 50%, ignore it and do not capture. However, you must always allow the user to trigger this manually and bypass the confidence check if they explicitly request a capture.

Determine Review Scope

  1. Identify Changed Files:
    • If the user provided a diff or explicit instructions, follow them.
    • Otherwise, you MUST execute the platform-appropriate script with --json to detect changed files since the merge-base or in the working directory.
      • Linux/macOS: run the script at scripts/bash/detect-changed-files.sh --json
      • Windows: run the script at scripts/powershell/detect-changed-files.ps1 --json
      • When invoked via a Spec Kit command context that resolves {SCRIPT}, use the provided value directly.
    • Use the changed_files list as the primary set for knowledge extraction.

Durable Memory Context (Duplicate Prevention)

Before proposing new entries, check the existing memory to avoid duplicates.

  1. Refresh Cache: If memory search is empty or you need the latest state, call speckit_memory_refresh_cache(scope="memory") or npx speckit-memory refresh-memory to restore the SQLite cache from the backup .md files.
  2. Targeted Search: Call speckit_memory_search(query="architecture constraints boundaries decisions <topic>") for candidate topics identified from the diff.
  3. Read Results: Review the search results to ensure the candidate lesson is not already captured.
  4. Do NOT read .md memory files directly. MCP search results via SQLite are the single source of truth. The .md files are only backups managed by the extension.

Read the full file on GitHub · 112 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. 8d ago First seen · 112 lines · 13 tokens per session scan A a15951c1c175

Subscribe to this mod's changes

speckit.memory-md.capture-from-diff is a command published in the GitHub repository DyanGalih/spec-kit-memory-hub (15 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 1,391 once invoked, about $0.0001 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 2026-08-30.