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/coderbhoid/ai-format/agentic-skillnpx skills add CoderBhoid/ai-format --skill agentic-skillgit clone --depth 1 https://github.com/CoderBhoid/ai-formatWhat 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 | $0.00036 | $0.00991 |
| Opus 5 | $0.00018 | $0.00495 |
| Sonnet 5 | $0.00007 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
ai-context-saving 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 yesterday.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secure AI Context Saving & Restoring
This skill defines the standard operating procedures for saving, loading, and managing persistent cognitive checkpoints using the .ai file format, incorporating temporal memory decay and automatic keychain management.
Overview
Unlike raw text files (.md, .txt), the .ai file format stores compressed, post-quantum cryptographically secured representations of an agent's memory, context, and conversation logs. It allows agents to load large histories instantly, bypassing long input-prefill computation phases.
When to Save Context
You should proactively serialize and save active context to a .ai file in the following scenarios:
- Milestone Completion: After finishing a major coding phase, debugging loop, or architectural plan.
- Pre-Flight Checkpoint: Before running high-risk commands (e.g., database migrations, destructive git commands) to create a recovery state.
- Session Shutdown: When wrapping up a session or preparing to hand off work to another agent.
During serialization, the context engine applies Temporal Memory Decay:
- Fresh Context (< 1 Hour): Saved at
FP16_RAWresolution (100% detail retention). - Medium-term Context (< 1 Day): Pruned of redundant helper tokens and quantized to
INT8. - Ancient Context (> 1 Day): Condensed into high-level
INT2semantic concepts.
When to Load Context
You should search for and deserialize .ai files:
- Session Resumption: At the start of a task, if a previously saved
.aifile exists in the directory. - Shared Agent Handoff: If another agent has generated a context snapshot and passed it to you for continuation.
How to Interface with the .ai Format Engine
Use the system script ai_format_production.py to pack and unpack files. The script supports programmatic integration or shell calls.
1. Saving (Packing) Context
To pack a session context, prepare the metadata and payload dictionary, and call the python serialization tool:
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.
- yesterday First seen · 102 lines · 36 tokens per session scan A ff223b02436b
ai-context-saving is a skill published in the GitHub repository CoderBhoid/ai-format (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 991 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
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.