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 igapyon/igapyon-agent-skills --skill igapyon-agent-state-managementgit clone --depth 1 https://github.com/igapyon/igapyon-agent-skillsWrote 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/igapyon/igapyon-agent-skills/igapyon-agent-state-management)<a href="https://agentmods.dev/skills/igapyon/igapyon-agent-skills/igapyon-agent-state-management"><img src="https://agentmods.dev/badge/skills/igapyon/igapyon-agent-skills/igapyon-agent-state-management/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/igapyon/igapyon-agent-skills/igapyon-agent-state-management"><img src="https://agentmods.dev/badge/skills/igapyon/igapyon-agent-skills/igapyon-agent-state-management.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 | $0.00185 | $0.01282 |
| Opus 5 | $0.00093 | $0.00641 |
| Sonnet 5 | $0.00037 | $0.00256 |
| Haiku 4.5 | $0.00018 | $0.00128 |
Grade A, and why
igapyon-agent-state-management 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 10d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Igapyon Agent State Management
Set up, resume, and maintain a small repository-local Markdown state convention for AI agent work:
GOAL.md: define the objective, completion conditions, and stop conditionsTODO.md: track active tasks, blockers, and repeated failuresDECISIONS.md: record important decisions and reasonsHANDOFF.md: summarize the current state for the next human or agent
This is a repository workflow skill, not a character-agent, model, editor, or vendor-specific workflow.
Trigger Phrases
This skill intentionally uses hard triggers. Use it only for the frontmatter description triggers. Useful user-facing phrases:
igapyon 状態管理igapyon 作業状態igapyon 作業再開igapyon goaligapyon todoigapyon handoffigapyon GOAL TODO DECISIONS HANDOFF
When answering "what skills are available?", describe this as the skill for
igapyon 状態管理 and igapyon 作業再開.
Use index.json before reading multiple references.
Core Workflow
- Inspect the repository before editing.
- Check whether
GOAL.md,TODO.md,DECISIONS.md, orHANDOFF.mdalready exist. - Do not overwrite existing files without reading them first.
- If
TODO.mdalready exists, preserve its existing purpose and add or update only## AI Agent Current Taskswhen appropriate. - Use references/markdown-state-files.md for setup, resume, existing-file handling, README notes, harness-operation decisions, interruption handling, and templates.
- When a root
README.mdexists, add or propose a short AI-agent note that points agents toGOAL.md,TODO.md,DECISIONS.md, andHANDOFF.md. - Use templates from templates/ when creating new files.
- Keep the state files lightweight. Do not turn them into long work logs or broad project documentation.
Resume Workflow
When the user says igapyon 作業再開, recover the current repository working
state; do not assume new files should be created.
What ships with it
8 files 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.
- 10d ago First seen · 103 lines · 185 tokens per session scan A aa1a9c54481b
igapyon-agent-state-management is a skill published in the GitHub repository igapyon/igapyon-agent-skills (2 stars, last pushed 26d ago), licensed Apache-2.0. It adds 185 tokens to every session and 1,282 once invoked, about $0.0009 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
learn
A workspace memory workflow for recording writing preferences, style guidance, and successful story hooks. It stores them as project assets rather than in a separate memory file.
Apple Notes
Open Notes.app and create or update iCloud notes on macOS using memo when possible and AppleScript when direct app automation is more reliable.
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.