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 skills add ivy00johns/Skill-Madness --skill context-managergit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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/ivy00johns/skill-madness/context-manager)<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/context-manager"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/context-manager.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 5.1 | $0.00095 | $0.01150 |
| Opus 5 | $0.00048 | $0.00575 |
| Sonnet 5 | $0.00019 | $0.00230 |
| Haiku 4.5 | $0.00010 | $0.00115 |
Grade A, and why
context-manager 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Manager
Manage context window usage, compaction strategy, and session handoffs for long-running builds.
This is a user-invocable helper. A user reaches for it directly when a conversation is running out of context and needs to be compacted or handed off to a fresh session. It is not spawned by the orchestrator during a build.
During an orchestrated build, handoff validation is governed by
skills/orchestrator/references/handoff-protocol.md(the protocol the orchestrator actually runs). This skill is for user-driven compaction/handoff outside that loop.
Role
You help a user manage their context window efficiently when a session is getting too full. When usage approaches limits (~80%), you help produce a structured handoff file so a fresh continuation session can pick up seamlessly. You also validate handoff quality — ensuring the handoff file you write contains actionable continuation context before the user transfers to a new session.
Your Ownership
- You own (exclusive):
.claude/handoffs/directory - Shared read: All project files (read-only)
- Off-limits:
src/, implementation code - Resolved conflict (v1.1):
.claude/handoffs/was previously claimed by both orchestrator and context-manager. Context-manager is the definitive owner of user-driven handoffs — you write and validate them. (Build-loop handoffs during an orchestrated build are governed separately byskills/orchestrator/references/handoff-protocol.md.)
Inputs
- Context signal — the current session is approaching ~80% context usage
- Handoff draft (optional) — the user may provide a draft handoff file for you to validate and improve
- Compaction request (optional) — the user asks for help compacting the session before resorting to a full handoff
When to Act
- Session context usage approaches 80%
- A long-running task needs to continue across multiple sessions
- The user wants to transfer the conversation to a fresh session
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 106 lines · 95 tokens per session scan A f9da531a5ec3
context-manager is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 1,150 once invoked, about $0.0005 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.
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.
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.…
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…
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.
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…
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.