What is devin-conversation-recovery?

A method for finding and reading old Devin coding-agent conversations stored in local SQLite databases. It recovers session details and message contents from past sessions.

Use it to search past Devin sessions, inspect their titles and messages, and recover details from earlier work.

It helps restore context when an earlier agent conversation is no longer visible in the current workspace.

devin-conversation-recovery — Skill for Claude Code and Codex by jxoes

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/jxoesneon/Ciel

agentmods

npx agentmods add skills/jxoesneon/ciel/devin-conversation-recovery

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jxoesneon/ciel/devin-conversation-recovery/github.svg)](https://agentmods.dev/skills/jxoesneon/ciel/devin-conversation-recovery)

Your own site

<a href="https://agentmods.dev/skills/jxoesneon/ciel/devin-conversation-recovery"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/devin-conversation-recovery/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jxoesneon/ciel/devin-conversation-recovery"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/devin-conversation-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 862 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.00862
Opus 5	$0.00017	$0.00431
Sonnet 5	$0.00007	$0.00172
Haiku 4.5	$0.00003	$0.00086

Measured 4d ago against content hash b772934ddc72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

devin-conversation-recovery 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 4d 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.

skills/devin-conversation-recovery/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CIEL ADAPTATION: Devin Conversation Recovery

This skill locates and extracts past Devin CLI/ACP conversations from local SQLite stores on disk. Devin runs as an ACP provider inside Windsurf ("Devin Local") — conversations are NOT in Hermes's session DB. This is a conversation archaeology primitive for recovering context lost between sessions. Ciel's autonomy ladder gates filesystem reads of credential-bearing stores — any secrets encountered trigger user escalation.

Storage Layout

Session metadata: ~/Library/Application Support/Devin/User/globalStorage/state.vscdb → ItemTable keys windsurf.acp.sessioninfo.session.* and windsurf.acp.messageStore.index (maps sessionId → message-db uuid).
Message bodies: ~/Library/Application Support/Devin/User/acp-messages/<uuid>.db → table messages(position, kind, payload); payload is JSON with streaming text chunks plus tool_call rows carrying rawInput and exit codes.

Quick Path: Helper Script

python ~/.ciel/skills/devin-conversation-recovery/scripts/find_devin_convo.py --list
python .../find_devin_convo.py "blender-mcp"          # titles + first messages
python .../find_devin_convo.py "search text" --deep   # grep ALL payloads (slow)
python .../find_devin_convo.py --extract <uuid> -o /tmp/convo.txt

Extract output is plain text (=== [position] kind sections). Full transcripts can exceed 1M chars — dump to a file and page through rather than printing.

Manual Procedure

List sessions: Query state.vscdb for windsurf.acp.sessioninfo.session.% keys; parse messageStore.index JSON for uuid mapping.
Search bodies: Iterate all acp-messages/*.db files, substring-match against payload column.
Extract: Payloads are JSON; payload.content is either a dict or a list of chunk dicts — handle both shapes. Kinds: agent_message, agent_thought, plan, subagent, tool_call.

Safety Considerations

These SQLite stores may contain credentials, API keys, or PII from past tool calls.
Ciel's autonomy ladder escalates to the user when secrets are detected in extracted content.
Never print raw transcripts to shared logs — always write to a local file first.
Also check User/workspaceStorage/*/state.vscdb for backup copies.

Read the full file on GitHub · 58 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.

4d ago Changed b772934ddc72
8d ago First seen · 58 lines · 34 tokens per session scan A 01026ca8486a

Subscribe to this mod's changes

devin-conversation-recovery is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 34 tokens to every session and 862 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 2026-09-03.

Autonomous Agents Building agents Claude Code Memory and context agentic-workflows ai ciel domain:ops gemini-cli harmonized multi-agent-systems

build-personal-brain

Create, resume, validate, connect, or maintain a private cross-project memory for AI assistants. Use when a person asks to build a personal memory from local work folders and past assistant conversations, continue an interrupted memory audit, connect an existing memory to another local assistant, verify that the…

mikeshu2001/personal-brain-builder · 81 tokens

squad-bootstrap

Skill de inicialização da squad. Faz a varredura do projeto e popula a memória técnica e de negócios em memories/. ATENÇÃO - SÓ DEVE ser executada se houver solicitação explícita do usuário ("instalar a squad", "fazer setup inicial", "bootstrap do projeto") ou logo após o instalador (install.sh) ter configurado a…

rcelebrone/DotAgents · 84 tokens

devin-conversation-recovery