escalate

A way to ask a fresh specialist agent to solve one narrowly defined task when the main coding session is stuck. The specialist returns a plan, one focused change, a verification result, and a short lesson.

In plain words
What is it for?
Use it for a bounded debugging or implementation subtask, especially when the main agent cannot identify the next safe change.
Why use it?
A clean context can help resolve a specific problem without expanding the task into unrelated redesign or refactoring.

Agent

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.

agentmods
npx agentmods add agents/rasputinkaiser/self-improvement-plugin/escalate
Clone the repo
git clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-Plugin
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 243 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.00243
Opus 5 $0.00018 $0.00121
Sonnet 5 $0.00007 $0.00049
Haiku 4.5 $0.00004 $0.00024

Measured 2d ago against content hash 95b5558ced16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

escalate 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 2d 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.

agents/escalate.md · 20 lines

What it actually says

You are the escalation specialist. The main thread has handed you ONE bounded subtask it could not resolve. You run on the SAME model as the session — your advantage is a clean context window, a tight toolset, and a forced structured output. Constraints:

  • Do the minimum to unblock; do not re-architect or refactor unrelated code.
  • Prefer reading before writing. State your plan in 3 bullets before editing.
  • Make one focused change, then verify it (run the relevant test or smoke check).

End your turn with exactly two blocks:

  1. DIFF: a unified diff of every change you made.
  2. LESSON: one line (<=140 chars) capturing what made the difference, scoped to the touched file/topic. This will be recorded to Memory Fabric so the main thread recalls it next time and doesn't need to re-escalate.
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.

  1. 2d ago First seen · 20 lines · 37 tokens per session scan A 95b5558ced16

Subscribe to this mod's changes

escalate is an agent published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (6 stars, last pushed 5d ago), licensed MIT. It adds 37 tokens to every session and 243 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.

Related

Other agents, from other repositories

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

artifact-coverage-reviewer

Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…

juicesharp/rpiv-mono · 102 tokens

prompting-tutorials

This page documents the best-performing LLM prompts for creating SolidWorks parts via the MCP server. Each recipe shows the exact sequence of tool calls and the prose prompt that reliably produces them from a general-purpose LLM (Claude, GPT-4o, etc.).

andrewbartels1/SolidworksMCP-python · 0 tokens

Music Producer

AI-powered music production specialist for premium soundscapes and commercial tracks.

frankxai/agentic-creator-os · 16 tokens

docs-app-builder

Use this agent to build a documentation application as a React app — from a repo's README, docs folder, or code. Trigger on "build a docs site", "documentation app for this project", "turn these docs into a website", "docs portal with navigation", or requests to make existing docs browsable/interactive. Returns a…

aayushostwal/nexus · 97 tokens

(@_@) engineer

Technical feasibility assessment, architecture review, and implementation complexity analysis. Use when evaluating technical specs, reviewing PRDs for engineering feasibility, estimating implementation effort, or getting feedback on system design decisions.

carlvellotti/free-ai-courses · 43 tokens