agentmods.dev

skill-session-state

A session-state system that saves an agent's current mode, task, and summary so work can continue after a reset.

In plain words
What is it for?
It stores the latest task state in a local session file and restores that context at the start of a new session.
Why use it?
It prevents important context from being lost when the session window is cleared or restarted.

Skill for Claude CodeCodex

5 19d ago A scan 21 tokens original Apache-2.0
View the source file MatrixFounder/Agentic-development
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 skills/matrixfounder/agentic-development/skill-session-state
Any agent
npx skills add MatrixFounder/Agentic-development --skill skill-session-state
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,181 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 $0.00021 $0.01181
Opus 5 $0.00010 $0.00590
Sonnet 5 $0.00004 $0.00236
Haiku 4.5 $0.00002 $0.00118

Measured 2d ago against content hash bc1607a81058, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-session-state 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/tests/test_update_state.py, scripts/update_state.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agent/skills/skill-session-state/SKILL.md · 103 lines

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.

Session State Management

This skill provides the mechanism to persist your current working state to a file. This allows you to "reboot" from a seamless context state if the session window is reset.

1. The Session File

  • Path: .agent/sessions/latest.yaml — resolved from the repo root regardless of the invocation CWD (walk-up to .git, CLAUDE_PROJECT_DIR fallback; SS-1).
  • Purpose: Stores the exact arguments from your last task_boundary call, plus session metadata.
  • Persistence: surviving session clears, allowing you to pick up exactly where you left off.
  • Never committed: this is per-machine runtime data — .agent/sessions/ is gitignored (SS-2). Do not git add it and do not ship a committed "seed" state.

2. Boot Protocol (Start of Session)

IF .agent/sessions/latest.yaml exists AND you are starting a new session (blank context):

  1. READ the file using read_file or view_file.
  2. RESTORE your state:
    • Set your internal Mode to the file's mode.
    • Set your TaskName and TaskStatus to the file's current_task.
    • Read the context_summary to understand what you were doing.
    • Check active_blockers to see if you were blocked.

3. Update Protocol (During Work)

First: can you execute at all? This skill is TIER 0 — it loads into every role, including the read-only reviewers and critics (task-reviewer, plan-reviewer, architecture-reviewer, critic-*), which are declared without an execution tool on purpose. If you have no way to run a command, this section does not apply to you: session state is the ORCHESTRATOR's to persist, you have no phase boundary of your own to record, and you should proceed to your actual task. Do not spend your turn attempting the command — a mandatory-sounding instruction that a role cannot satisfy is how a subagent burns its whole turn and returns nothing (skill-parallel-orchestration §2.4).

Read the full file on GitHub · 103 lines

Files

What ships with it

2 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.

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 · 103 lines · 21 tokens per session scan A bc1607a81058

Subscribe to this mod's changes

skill-session-state is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,181 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 2026-08-31.

Memory and contextagenticai-agentsclaude-codevdd
Related

Other skills, from other repositories

batch

Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.

QwenLM/qwen-code · 37 tokens

extension-creator

Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…

QwenLM/qwen-code · 96 tokens

notion

Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.

elizaOS/eliza · 69 tokens

pr-feedback

Fetches PR review feedback and inline comments, categorizes them, and presents options to the user. Use when the user asks to get, read, address, or fix review comments on a pull request.

strands-agents/harness-sdk · 44 tokens

argent-native-profiler

Native profiling for CPU hotspots, UI hangs, memory issues. iOS via xctrace; Android via Perfetto. Use when diagnosing native-level performance issues.

software-mansion/argent · 37 tokens

argent-tv-interact

Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…

software-mansion/argent · 107 tokens