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.
npx agentmods add skills/gentech-labs/gentech-agent-kit/context-cycle-proactivenpx skills add Gentech-Labs/genTech-agent-kit --skill context-cycle-proactivegit clone --depth 1 https://github.com/Gentech-Labs/genTech-agent-kitWrote 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/skills/gentech-labs/gentech-agent-kit/context-cycle-proactive)<a href="https://agentmods.dev/skills/gentech-labs/gentech-agent-kit/context-cycle-proactive"><img src="https://agentmods.dev/badge/skills/gentech-labs/gentech-agent-kit/context-cycle-proactive.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.01719 |
| Opus 5 | $0.00024 | $0.00860 |
| Sonnet 5 | $0.00010 | $0.00344 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
context-cycle-proactive 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 4d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Cycle — Proactive Save & Resume
When to Use
- Conversation/working context reaches 80-90% and you can't make room (the trigger).
- Mid-way through a big build and you hit a natural stopping point.
- The user says "save progress," "start new," "load a new context," or "/new."
- You notice memory pressure and want to save before it drops the ball.
The Problem This Solves
Even with a large context window, active build sessions fill up fast. When context hits ~80-90% and you can't make room, the session degrades and work gets dropped. This is the proactive protocol: you detect the pressure, save your place to the brain, route the log to the right channel, load a fresh context, and pick the task back up.
The Cycle — 5 Steps (Save → Route → Load → Resume)
Step 1: SAVE progress to the brain (vault / second brain)
Write a dated progress file to the vault so nothing is lost. Use the context bridge generator if available, then fill it in:
python3 <path-to>/session-hygiene/scripts/context-save.py # if present in the agent
Capture the real content (bridge path varies by setup; the principle is the same):
- Active work: what you were building, current task, dependencies
- Decisions made: the calls taken + reasoning
- Blockers: anything stuck or needing the user/another lane
- Next steps: the exact resume point, so the next session picks up cleanly
Rule: Save where you are BEFORE you move on. Never let memory fill up and drop the ball.
Step 2: ROUTE the log to the right channel
Decide where the progress note belongs. This is the agent's judgment call — where does this work need to live, and who needs to see it?
| Content | Channel / folder |
|---|---|
| Coordination, decisions, blockers, status | HQ (your main group, 00-HQ/) |
| Ideas, considerations, open questions | Mess Hall (11-Mess Hall/considerations.md) |
| Heavy build / code / dev progress | Labs (01-HANDOFFS/gentech-to-labs/) |
| Finance / treasury / yield | Treasury (01-HANDOFFS/gentech-to-treasury/) |
| Content / social / hackathon | Entertainment (01-HANDOFFS/gentech-to-entertainment/) |
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.
- 4d ago First seen · 126 lines · 48 tokens per session scan A 9fdc9d068aac
context-cycle-proactive is a skill published in the GitHub repository Gentech-Labs/genTech-agent-kit (0 stars, last pushed 13d ago), licensed MIT. It adds 48 tokens to every session and 1,719 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.
Other skills, from other repositories
kb-memory
Use when knowledge base and memory system for AI agents. Covers company KB, persistent memory, session recall, and brain architecture for context preservation.
engineer-brain
Your self-updating engineering brain — tracks work patterns, expertise, habits, progress gaps, and generates daily sync-up notes and quarterly review content. Invoke when you say "engineer brain", "update brain", "daily sync", "standup", "sync up", "quarterly connections", "what did I work on", "my progress", "where…
team-brain
Team / initiative shared AI memory. User triggers once with start; then sync mode pulls crew memory and agents remember findings (merge-safe). Invoke for team-brain, start, stop, wake, sync, shared spike, initiative, Jira crew work, remember, recall, breakdown (not personal standups).
brain-save
Saves a single fact, decision, pattern, or convention into your governed knowledge brain so it can be recalled later — and retires memories that are outdated. Side-effecting: it writes to your durable corpus, so it never auto-fires — invoke it explicitly. Use when you want the brain to remember something specific…
handoff-revive
Save a compact handoff checkpoint and resume work in a fresh session without replaying the entire transcript via --resume. SAVE trigger — the slash command /handoff-revive:save (carries forward still-relevant goal/decisions/lessons from any existing handoff, then runs a content-quality check). AUTO-SAVE trigger — when…
context-manager
Context management skill providing discovery, fetching, harvesting, extraction, compression, organization, cleanup, and guided workflows for project context.