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/agenttoolkit/altk-evolve/evolve-lite-savenpx skills add AgentToolkit/altk-evolve --skill evolve-lite-savegit clone --depth 1 https://github.com/AgentToolkit/altk-evolveWhat 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 | $0.00028 | $0.03116 |
| Opus 5 | $0.00014 | $0.01558 |
| Sonnet 5 | $0.00006 | $0.00623 |
| Haiku 4.5 | $0.00003 | $0.00312 |
Grade A, and why
evolve-lite:save 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.
How it starts
The opening of the file, as written. The whole thing — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Session as Skill
Overview
This skill analyzes your current successful session and generates a new reusable skill with:
- SKILL.md: Comprehensive documentation with workflow steps, parameters, and examples
- Helper scripts: Python scripts for any programmatic operations identified in the workflow
It extracts the workflow pattern from your conversation history (user requests, reasoning steps, tool calls, and responses) and creates parameterized files that can be invoked in future sessions.
Use this skill when you've completed a task successfully and want to save the workflow for future reuse.
When to Use
- After completing a multi-step task successfully
- When you've discovered a useful workflow pattern
- When you want to standardize a process for future use
- After solving a problem that might recur
- When the workflow involves programmatic operations that could benefit from helper scripts
Workflow
Step 1: Review Current Session
Analyze the conversation history available in the current context, which includes:
- User messages: All requests and questions from the user
- Assistant reasoning: Thinking tags and decision-making process
- Tool calls: All tools invoked with their arguments
- Tool responses: Results and outcomes from each tool
- Final outcome: The successful result achieved
Action: Review the entire conversation from start to current point
Step 2: Identify the Workflow Pattern
Extract the high-level workflow by:
- Identifying the goal: What was the user trying to accomplish?
- Grouping related actions: Which tool calls belong together as logical steps?
- Recognizing decision points: Where did the workflow branch based on conditions?
- Noting error handling: How were errors or edge cases handled?
- Extracting the sequence: What is the step-by-step process?
Example Pattern Recognition:
User Goal: "Read a file and display its contents"
Workflow Pattern:
1. Attempt to read file at expected location
2. If access denied → check allowed directories
3. Search for file in allowed directories
4. Read file from correct location
5. Format and present results
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.
- 2d ago First seen · 471 lines · 28 tokens per session scan A 1598cb320954
evolve-lite:save is a skill published in the GitHub repository AgentToolkit/altk-evolve (105 stars, last pushed 7d ago), licensed Apache-2.0. It adds 28 tokens to every session and 3,116 once invoked, about $0.0001 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
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
kungfu-agent-onboarding
Discover the exact Kungfu Project, WorkConsole, WorkRef, Skill catalog, and Core Work state admitted to this Amp process.
Context Doctor
Identify and repair degradation in system prompt, external memory, and skills preventing you from following instructions or remembering information as well as you should.
generating-mod-envs
Generates and reviews mod learning env JSON files for Letta Code local mods. Use when asked to teach, learn, or optimize a mod behavior; create, draft, validate, improve, or explain envs for /mods learn --env; or design evaluation scenarios, memory fixtures, requiredResultMarkers, requiredTraceMarkers, negative…
letta-guide
Read the official Letta documentation (docs.letta.com) through its cached, ETag-checked fetch route. Load before ANY docs.letta.com retrieval — answering how Letta works, what Letta (or you) can do, setting up providers, models, channels, skills, memory, schedules, permissions, self-hosting, pricing, or billing, AND…
adding-models
Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update model-specific compatibility behavior. Covers runtime catalog sources, CI test matrices, and handle validation.