opencode-memory
Skill113 starsChanged 5 months agoApache-2.0View on GitHub
Browse local OpenCode history: sessions, messages, plans, prompt history, and prior decisions. Use when the user says history, previous session, last time, remember, recall, plans, prior work, or when resuming/debugging repeated work where earlier OpenCode context may help. Do not use for fresh tasks or when current files/git already answer the question.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- R44VC0RP/skillstheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- R44VC0RP/skills★ 161same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- design-explorationSkill
- grok-cliSkill
- x-algorithmSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Read-only lookup for local OpenCode history.
- Distinctive: line 24
Do not use when repo files/git already answer the question or the task is new.
- Distinctive: line 28
Read-only. Never modify OpenCode DB/files.
- Very specific: line 29
Use sqlite3 with read-only URI.
- Very specific: line 30
Keep results small with LIMIT and targeted LIKE.
- Very specific: line 32
Avoid auth/provider tables: account, credential, control_account, account_state.
- Distinctive: line 36
Run this first in bash:
- Distinctive: line 141
Use references/storage-format.md only when you need table details, part/tool shapes, legacy JSON paths, or debug queries.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
OpenCode Memory Browser
Read-only lookup for local OpenCode history. Use it only when prior sessions, plans, or decisions would help. Do not inject history by default.
Use When
- User asks for history, previous sessions, last time, plans, recall, or memory.
- Resuming a project where prior OpenCode context may matter.
- Debugging a repeat issue that may have appeared earlier.
Do not use when repo files/git already answer the question or the task is new.
Rules
- Read-only. Never modify OpenCode DB/files.
- Use
sqlite3with read-only URI. Do not read the DB with file-read tools. - Keep results small with
LIMITand targetedLIKE. - Summarize relevant findings; do not dump raw history.
- Avoid auth/provider tables:
account,credential,control_account,account_state.
Setup
Run this first in bash:
DATA_ROOT="${XDG_DATA_HOME:-$HOME/.local/share}/opencode"
STATE_ROOT="${XDG_STATE_HOME:-$HOME/.local/state}/opencode"
DB="$(opencode db path 2>/dev/null || true)"
[ -n "$DB" ] || DB="${OPENCODE_DB:-$DATA_ROOT/opencode.db}"
case "$DB" in :memory:|/*) ;; *) DB="$DATA_ROOT/$DB" ;; esac
if [ ! -f "$DB" ]; then
for candidate in "$DATA_ROOT"/opencode*.db; do
[ -f "$candidate" ] && DB="$candidate" && break
done
fi
DB_URI="file:${DB}?mode=ro"Useful files:
- Plans:
$DATA_ROOT/plans/*.md - Prompt history:
$STATE_ROOT/prompt-history.jsonl - Session diffs:
$DATA_ROOT/storage/session_diff/<session-id>.json
Queries
Summary
sqlite3 "$DB_URI" "
SELECT 'projects', COUNT(*) FROM project
UNION ALL SELECT 'main sessions', COUNT(*) FROM session WHERE parent_id IS NULL
UNION ALL SELECT 'messages', COUNT(*) FROM message
UNION ALL SELECT 'parts', COUNT(*) FROM part
UNION ALL SELECT 'todos', COUNT(*) FROM todo;
"Recent sessions
sqlite3 "$DB_URI" "
SELECT s.id, COALESCE(s.title, 'untitled') AS title,
COALESCE(p.name, p.worktree, '') AS project,
datetime(s.time_updated/1000, 'unixepoch', 'localtime') AS updated,
(SELECT COUNT(*) FROM message m WHERE m.session_id = s.id) AS messages
FROM session s
LEFT JOIN project p ON p.id = s.project_id
WHERE s.parent_id IS NULL
ORDER BY s.time_updated DESC
LIMIT 10;
"Search text
Replace SEARCH_TERM first.
sqlite3 "$DB_URI" "
SELECT s.id, COALESCE(s.title, 'untitled') AS title,
json_extract(m.data, '$.role') AS role,
datetime(m.time_created/1000, 'unixepoch', 'localtime') AS time,
substr(json_extract(p.data, '$.text'), 1, 200) AS snippet
FROM part p
JOIN message m ON m.id = p.message_id
JOIN session s ON s.id = m.session_id
WHERE s.parent_id IS NULL
AND json_extract(p.data, '$.type') = 'text'
AND json_extract(p.data, '$.text') LIKE '%SEARCH_TERM%'
ORDER BY m.time_created DESC
LIMIT 10;
"Read session text
Replace SESSION_ID_HERE first. Text parts only; use the reference for tool,
patch, file, reasoning, or V2 internals.
sqlite3 "$DB_URI" "
SELECT json_extract(m.data, '$.role') AS role,
datetime(m.time_created/1000, 'unixepoch', 'localtime') AS time,
GROUP_CONCAT(json_extract(p.data, '$.text'), char(10)) AS text
FROM message m
LEFT JOIN part p ON p.message_id = m.id
AND json_extract(p.data, '$.type') = 'text'
WHERE m.session_id = 'SESSION_ID_HERE'
GROUP BY m.id
ORDER BY m.time_created ASC
LIMIT 50;
"Plans And Prompt History
ls -lt "$DATA_ROOT"/plans/*.md 2>/dev/null | head -20
tail -20 "$STATE_ROOT"/prompt-history.jsonl 2>/dev/nullPrompt history entries currently use input, mode, and parts[]; do not
assume root text.
Deep Reference
Use references/storage-format.md only when you need table details, part/tool shapes, legacy JSON paths, or debug queries.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

