resume-from-chat-history

resume-from-chat-history is a skill for Claude Code from aiya000/dotfiles. It costs 112 tokens per session (2,451 once invoked), scanned A, original, MIT.

A recovery workflow for continuing a Kiro coding chat after it breaks or is lost by reading the saved session files on disk.

In plain words
What is it for?
It helps locate the relevant session by working directory and reconstruct the conversation from Kiro’s JSON and JSONL history files.
Why use it?
It restores earlier decisions, requests and unfinished work when the current conversation no longer contains the needed context.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Good fit It helps locate the relevant session by working directory and reconstruct the conversation from Kiro’s JSON and JSONL history files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiya000/dotfiles/resume-from-chat-history
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.

Any agent
npx skills add aiya000/dotfiles --skill resume-from-chat-history
Clone the repo
git clone --depth 1 https://github.com/aiya000/dotfiles

Made for: Claude Code.

Wrote 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.

agentmods badge for resume-from-chat-history

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiya000/dotfiles/resume-from-chat-history/github.svg)](https://agentmods.dev/skills/aiya000/dotfiles/resume-from-chat-history)
Your own site
<a href="https://agentmods.dev/skills/aiya000/dotfiles/resume-from-chat-history"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/resume-from-chat-history/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.

agentmods 80×15 button for resume-from-chat-history

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiya000/dotfiles/resume-from-chat-history"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/resume-from-chat-history.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,451 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00112 $0.02451
Opus 5.5 $0.00045 $0.00980
Sonnet 5.5 $0.00022 $0.00490
Haiku 4.5 $0.00011 $0.00245

Measured 15d ago against content hash 7b98dd6ddec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

resume-from-chat-history 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 15d 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.

.kiro_global/skills/resume-from-chat-history/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resume from chat history

Rebuild the context of a broken or lost Kiro chat from the auto-saved session files on disk, then hand off cleanly so work continues without losing decisions or the mid-task position.

Background: where Kiro keeps chat history

Kiro CLI auto-saves every conversation turn to per-directory session files under:

~/.kiro/sessions/cli/
├── {session_id}.json     # metadata: cwd, title, created_at, updated_at, session_state
├── {session_id}.jsonl    # append-only conversation log (one JSON object per line)
├── {session_id}.history  # prompt history
└── {session_id}.lock     # present ONLY while that session is actively running

Key facts this skill relies on:

  • Sessions are keyed by working directory (cwd field in the .json).
  • The currently running session has a .lock file; a broken/ended one does not (a stale lock can remain after a crash, so also use updated_at and cwd to disambiguate).
  • The .jsonl log holds the real content. Each line is one JSON object with a kind field:
    • kind: "Prompt" → a user message. Text lives in data.content[] items where kind == "text" (field data).
    • kind: "AssistantMessage" → an assistant message (its data.content may be a plain string or a list).
    • kind: "ToolResults" → tool outputs (usually skip when reconstructing intent).
  • There is no built-in content search; use rg over the .jsonl files.

When to use

  • The user reports the previous chat broke or was lost: "壊れた", "落ちた", "また壊れた", "the chat broke".
  • The user asks to hand off / resume: "引き継いで", "続きから", "内容読んで引き継げる", "resume the prior work".
  • The current session clearly lacks context for work already in progress — e.g. a feature branch is checked out with many uncommitted changes, but nothing in this session explains them.

If the user instead wants to re-run a stalled tool call inside the same live session, that is the next skill, not this one.

Workflow

1. Establish the current working directory and in-progress work

Read the full file on GitHub · 184 lines

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. 15d ago First seen · 184 lines · 112 tokens per session scan A 7b98dd6ddec2

Subscribe to this mod's changes

resume-from-chat-history is a skill published in the GitHub repository aiya000/dotfiles (21 stars, last pushed 2d ago), licensed MIT. It adds 112 tokens to every session and 2,451 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-01.