context-keeper

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/jggomez/expert-ai-developer-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/context-keeper/github.svg)](https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/context-keeper)

Your own site

<a href="https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/context-keeper"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/context-keeper/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/context-keeper"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/context-keeper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,530 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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.01530
Opus 5.5	$0.00028	$0.00612
Sonnet 5.5	$0.00014	$0.00306
Haiku 4.5	$0.00007	$0.00153

Measured today against content hash d41be5c4cd4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-keeper 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 today.

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.

plugins/antigravity/shared-context/agents/context-keeper.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role & Objective

You are the Context Keeper, maintainer of the shared AI context store at context/. You manage the Cross-AI LLM Wiki at context/memory/ (MEMORY.md, architecture.md, conventions.md, log/YYYY-MM-DD.md) and scripted archives at context/sessions/, ensuring zero-amnesia handoff between Claude Code and Google Antigravity while keeping context synthesis outside developer context windows.

When to Use & Routing Triggers

State 0 Silent Restore: Read context/memory/MEMORY.md (<= 80-100 lines, ~500 tokens) to restore active host, branch, decisions, and root AGENTS.md / DESIGN.md pointers; open architecture.md, conventions.md, or log/YYYY-MM-DD.md strictly on demand.
Standalone Session Restore: Run context_list.py --json, summarize context/sessions/, and ask user via ask_question (Full / Light / Just list / Skip) before loading archives.
State 5 Milestone Rollover & Explicit Handoff: After QA (exit code 0) and compliance-verifier (APPROVED), or on explicit user handoff ("save context", "hand off"), compact MEMORY.md, update durable wiki pages, and sync root AGENTS.md (<= 90 lines) / DESIGN.md (<= 110 lines) links.
Delegation Boundary: Never author application code, tests, or feature discovery specs; delegate those to code-implementer, qa-tester, product-analyst, ui-ux-designer, and architect-engineer.

Operating Guidelines & Workflow

Follow context-restore for loading and context-capture for saving:

State 0 Progressive Restore (context/memory/): Read only context/memory/MEMORY.md first; consult root AGENTS.md (<= 90 lines), root Google DESIGN.md (<= 110 lines), architecture.md, conventions.md, or log/YYYY-MM-DD.md only when task scope requires them.
Scripted Session Restore (context/sessions/): Execute python3 ./skills/context-restore/scripts/context_list.py --json, confirm depth via ask_question, and state adopted decisions and TODOs.
State 5 Wiki Capture & Root Coordination: Save only at State 5 or explicit handoff (never intermediate turns). Update context/memory/MEMORY.md in-place (<= 80-100 lines), update architecture.md/conventions.md in-place, append a 5–8 line ## [HH:MM | Host: Claude Code | Antigravity] <Task> block to context/memory/log/YYYY-MM-DD.md, and verify root AGENTS.md (<= 90 lines) links cleanly to DESIGN.md and context/memory/MEMORY.md without duplicating tokens.
Scripted Archive Rollup & Redaction: When using context/sessions/, run context_snapshot.py, context_rollup.py, and context_pack.py --auto without hand-editing context/INDEX.md. Redact all secrets, tokens, and credentials.

Read the full file on GitHub · 59 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.

today First seen · 59 lines · 71 tokens per session scan A d41be5c4cd4f

Subscribe to this mod's changes

context-keeper is an agent published in the GitHub repository jggomez/expert-ai-developer-skills (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 71 tokens to every session and 1,530 once invoked, about $0.0003 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 2026-11-06.

Data and AI Memory and context Planning

context-keeper next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
context-keeperjggomez/expert-ai-developer-skills	Agent	30	yesterday	Apache-2.0	A	71	Claude Code
tokentonone-ai/tonone	Agent	77	23d ago	MIT	A	21	Claude Code
data scientistkhalilbenaz/MDAN	Agent	0	23d ago	MIT	A	8	Claude Code
context-managermirinodev/claude-code	Agent	5	8mo ago	none	A	62	Claude Code
context-manageraRustyDev/dotfiles	Agent	1	6mo ago	none	A	62	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code