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 mkonstan/llm-tools --skill context-transfergit clone --depth 1 https://github.com/mkonstan/llm-toolsWrote 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/mkonstan/llm-tools/context-transfer)<a href="https://agentmods.dev/skills/mkonstan/llm-tools/context-transfer"><img src="https://agentmods.dev/badge/skills/mkonstan/llm-tools/context-transfer/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/skills/mkonstan/llm-tools/context-transfer"><img src="https://agentmods.dev/badge/skills/mkonstan/llm-tools/context-transfer.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 | $0.00156 | $0.01058 |
| Opus 5.5 | $0.00062 | $0.00423 |
| Sonnet 5.5 | $0.00031 | $0.00212 |
| Haiku 4.5 | $0.00016 | $0.00106 |
Grade A, and why
context-transfer 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 2mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Transfer
Generate structured state documents for AI cold-start recovery across any conversation type.
When To Use
- User asks to checkpoint, snapshot, or save state
- Session is getting long and compaction insurance is needed
- Work will continue in a new session (handoff)
- Multi-session work needs persistent state
- User mentions compaction, context loss, or continuity concerns
- Any conversation where accumulated decisions, findings, or state would be costly to lose
Before Starting
Read the full protocol:
Read references/protocol_v2.4s.md
This contains the complete section definitions, templates, rules, and quality checklist.
Quick Reference
The context transfer has 11 sections. Scale to complexity — not every conversation needs all sections.
| Section | Purpose | Required? |
|---|---|---|
| I. What This Is | Identity + "It is NOT" correction | Always |
| II. Domain Context | Problem-space briefing | Multi-session+ |
| III. Architecture | System structure | Build/engineering work |
| IV. Decisions | Numbered with narrative WHY | When decisions exist |
| V. Current State | Step sequence or phase summary | Always |
| VI. Artifacts | File inventory with status | When files exist |
| VII. Anti-Drift Warnings | Observed/predicted failure modes | Multi-session+ |
| VIII. What NOT To Do | Catastrophic prohibitions | When applicable |
| IX. Glossary | Context-specific terms | Domain-specific |
| X. Open Questions | Unresolved issues | When they exist |
| XI. Recovery Pointer | Exact restart location + path | Always |
Minimum viable: Sections I, V, XI.
Workflow
- Read the protocol (
references/protocol_v2.4s.md) — understand all section rules - Assess scope — use Scaling Guide to determine which sections are needed
- Gather state from conversation — extract decisions, current step, artifacts, open questions
- Write each section following the protocol templates exactly
- Apply critical rules:
- §I must include "It is NOT..." correction sentence
- §IV decisions must have narrative WHY (mark
[inferred]if rationale not explicitly stated) - §VII every warning tagged
[observed]or[predicted] - §XI must include
Work lives in:(writeUNKNOWN — ask userif path not known)
- Run Quality Checklist from protocol
- Save to
/mnt/user-data/outputs/and present to user
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.
- 2mo ago First seen · 93 lines · 156 tokens per session scan A 4b7d7cca0674
context-transfer is a skill published in the GitHub repository mkonstan/llm-tools (2 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 156 tokens to every session and 1,058 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, source notes, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
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…