aida-remember-branch

aida-remember-branch is a skill for Claude Code from LWTlong/aida. It costs 49 tokens per session (639 once invoked), scanned A, original, MIT.

A procedure for recording important technical decisions from a completed feature branch as MADR decision records. A feature branch is a separate line of code changes made before merging.

In plain words
What is it for?
Use it at pull-request time or after merging a feature branch. It examines the branch history and diff, selects decisions worth preserving, and records them separately for future sessions.
Why use it?
It preserves the reasons behind non-obvious choices, workarounds, constraints, and intentional omissions so later developers understand the branch's decisions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the aida plugin — 13 skills, 1 command, 1 MCP server shipped together

Good fit Use it at pull-request time or after merging a feature branch. It examines the branch history and diff, selects decisions worth preserving, and records them separately for future sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lwtlong/aida/aida-remember-branch
View source ↗ LWTlong/aida
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.

Any agent
npx skills add LWTlong/aida --skill aida-remember-branch
Clone the repo
git clone --depth 1 https://github.com/LWTlong/aida

Made for: Claude Code.

Or install aida, the plugin that ships this one along with the rest of its 13 skills, 1 command, 1 MCP server.

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 aida-remember-branch

README.md
[![agentmods](https://agentmods.dev/badge/skills/lwtlong/aida/aida-remember-branch/github.svg)](https://agentmods.dev/skills/lwtlong/aida/aida-remember-branch)
Your own site
<a href="https://agentmods.dev/skills/lwtlong/aida/aida-remember-branch"><img src="https://agentmods.dev/badge/skills/lwtlong/aida/aida-remember-branch/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.

agentmods 80×15 button for aida-remember-branch

Your own site · 80×15
<a href="https://agentmods.dev/skills/lwtlong/aida/aida-remember-branch"><img src="https://agentmods.dev/badge/skills/lwtlong/aida/aida-remember-branch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 639 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 $0.00049 $0.00639
Opus 5 $0.00024 $0.00319
Sonnet 5 $0.00010 $0.00128
Haiku 4.5 $0.00005 $0.00064

Measured 8d ago against content hash 4615418832cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aida-remember-branch 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.

src/assets/skills/aida-remember-branch/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIDA Remember Branch

Goal

At the end of a feature branch, read the git diff and extract the important decisions that were made. Record each as a separate MADR decision so future Claude sessions know WHY the code is written this way.

Steps

Phase 1 — Read the Diff

Run git log <base>..<branch> --oneline and git diff <base>..<branch> to understand what changed. Use git rev-parse --abbrev-ref HEAD if you don't know the branch name, and git merge-base HEAD origin/main (or origin/master) to find the right base if main isn't clear.

Focus on:

  • Non-obvious choices (why this algorithm, this data shape, this approach)
  • Workarounds (what bug, external API constraint, or deadline forced a suboptimal solution)
  • Constraints discovered (e.g. "this API doesn't support pagination", "this table has no index on X")
  • Things intentionally NOT done (and why)

Phase 2 — Identify Decisions

For each potential decision, ask:

  • Is this obvious from the code name or structure alone? → skip
  • Would a developer unfamiliar with this PR be confused or make the wrong choice? → record it
  • Is it scoped to specific files, or does it affect the whole project?

Phase 3 — Record Each Decision

For each non-obvious decision, call the aida_remember MCP tool directly with:

  • title: "Use X for Y" or "Don't do X in this module" (active voice, specific)
  • context: the constraint, bug, or requirement that forced this choice
  • decision: what was chosen and why
  • consequences: what breaks if you undo it, what improves
  • paths: file glob patterns scoping this decision (e.g. ["src/auth/**"]) — if global, omit

Phase 4 — Summary

After recording all decisions, report:

Branch memory saved: N decisions recorded

Decision Paths
Use JWT refresh rotation src/auth/**
Skip ORM for bulk inserts src/ingestion/**
... ...

Run /aida:recall to review all decisions, or /aida:undo to reverse the last write.

Read the full file on GitHub · 56 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 · 56 lines · 49 tokens per session scan A 4615418832cd

Subscribe to this mod's changes

aida-remember-branch is a skill published in the GitHub repository LWTlong/aida (8 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 639 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 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens