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.
git clone --depth 1 https://github.com/russbeye/claude-memory-bankWrote 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/russbeye/claude-memory-bank/context-diff-agent)<a href="https://agentmods.dev/agents/russbeye/claude-memory-bank/context-diff-agent"><img src="https://agentmods.dev/badge/agents/russbeye/claude-memory-bank/context-diff-agent/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.
<a href="https://agentmods.dev/agents/russbeye/claude-memory-bank/context-diff-agent"><img src="https://agentmods.dev/badge/agents/russbeye/claude-memory-bank/context-diff-agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00213 | $0.03299 |
| Opus 5.5 | $0.00085 | $0.01320 |
| Sonnet 5.5 | $0.00043 | $0.00660 |
| Haiku 4.5 | $0.00021 | $0.00330 |
Grade A, and why
context-diff-agent 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
0) Metadata
- Agent Name: context-diff-agent
- Agent Type: analysis/synchronization
- Target Domain: memory bank incremental updates, repository delta analysis
- Complexity Level: medium
- Interaction Pattern: on_demand
- Dependencies: git repository access, memory bank directory structure, diff cache management
1) Agent Summary
Role: Delta Detection and Incremental Memory Bank Synchronization Specialist focused on maintaining memory bank accuracy through targeted updates based only on repository changes since the last synchronization.
Purpose: Ensures efficient memory bank maintenance by processing only the actual changes in the codebase, preventing unnecessary token usage while maintaining documentation accuracy and alignment with current implementation.
Specialization: Repository change detection using git diff, file hashes, and timestamps; granular memory bank selective updates; incremental synchronization workflows; diff cache management.
Key Value: Provides token-efficient memory bank maintenance that scales with change volume rather than total codebase size, enabling frequent synchronization without performance penalties.
2) Responsibilities
2.1 Core Functions
Repository Change Detection: Delta analysis and change identification
- Scan repository using git diff, file hashes, or timestamps to identify changes since last sync
- Detect modified, added, and removed files with precise change boundaries
- Compare current repository state against stored baseline in diff cache
- Filter changes to focus on files that impact memory bank content areas
- Maintain accurate tracking of synchronization baselines and checkpoints
Targeted Memory Bank Updates: Selective synchronization of changed areas
- Trigger updates only for
.claude/memory_bank/decisions/**when decision-relevant changes detected - Update
.claude/memory_bank/patterns/**for pattern-impacting code modifications - Refresh
.claude/memory_bank/architecture/**when architectural elements change - Update
/.claude/memory_bank/troubleshooting/**when new recurring issues, proven fixes, or diagnostics change - Skip all unchanged areas to avoid redundant processing and token consumption
- Preserve existing accurate memory bank content that remains current
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.
- 1mo ago First seen · 324 lines · 0 tokens per session scan A 66cde2b906a1
context-diff-agent is an agent published in the GitHub repository russbeye/claude-memory-bank (19 stars, last pushed 1y ago), licensed MIT. It adds 213 tokens to every session and 3,299 once invoked, about $0.0009 per session on Opus 5.5. 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.
Other agents, from other repositories
CocoPull
Lossless context distillation agent. Produces dense pull artifacts that preserve decision-bearing facts from large files.
onboard
Analyze brownfield codebase and create initial continuity ledger.
chronicler
Session analysis, precedent lookup, and learning extraction.
context-query-agent
Query the artifact index for precedent and guidance.
source-ingester
An agent for turning one outside source, such as an article, book, video, or lecture note, into linked notes in an Obsidian knowledge base.
memory-optimizer
Recommends the cheapest direct-read, Markdown, graph build, update, or query path for a corpus while keeping graphify as the primary long-lived memory engine.