Not in the top 1,000 by GitHub stars
grandamenium/dream-skill
Memory consolidation skill for Claude Code - replicates Anthropic's unreleased auto-dream feature. 4-phase consolidation with 24hr auto-trigger.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
228634143517 → 228634143517
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 228634143517
No earlier version was observed for comparison.
161GitHub stars
3stars in 7 days
1skill in this repository
0commits in 30 days
Heat
2.9- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- dream
/
How it works
dream
When your agent uses it
Memory consolidation skill for Claude Code. Scans session transcripts for corrections, decisions, preferences, and patterns, then merges findings into persistent memory files. Auto-triggers via native Stop hook every 24hrs. Inspired by how sleep consolidates human memory.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
3,605 tokensWhen the skill is activated
Reference documents
861 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- ONBOARDING (delete this section after setup is complete)
- END ONBOARDING
- How It Works
- Phase 1: ORIENT
- Phase 2: GATHER SIGNAL
- Phase 3: CONSOLIDATE
- Phase 4: PRUNE & INDEX
- Safety
- Verification
Scripts executed separately
dream-hook.shinstall.shshould-dream.shtest-dream.sh
Files
README.mddoc3,710 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesSKILL.mdcore14,057 bytesdream-hook.shruns1,110 bytesinstall.shruns4,483 bytesshould-dream.shruns1,925 bytestest-dream.shruns15,733 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- dream
Repository facts
- License
- No license detected
- Created
- Mar 24, 2026
- Last pushed
- Mar 24, 2026
- Forks
- 21
- Open issues
- 4
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 20 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 5 dangerous shell commandsin 3 files: SKILL.md:96 test-dream.sh:217 install.sh:119
- 11 network referencesin 2 files: test-dream.sh:65 README.md:41
- No hidden or obfuscated text
- No instruction overrides
- 4 executable scriptsin 4 files: dream-hook.sh:1 install.sh:1 should-dream.sh:1 and 1 more
- No access to secrets
- No requests to vote in Hot
Show all 20 signals by file
README.md
SKILL.md
- Dangerous shell operationline 96
If the file `~/.claude/.dream-pending` exists at session start, run `/dream` as a subagent in the background, then delete the flag file: `rm ~/.claude/.dream-pending`. This is the memory consolidation system - it runs automatically every 24 - Dangerous shell operationline 360
rm -f ~/.claude/.dream-pending
dream-hook.sh
- Executable scriptline 1
#!/usr/bin/env bash
install.sh
should-dream.sh
- Executable scriptline 1
#!/usr/bin/env bash
test-dream.sh
- Executable scriptline 1
#!/usr/bin/env bash - Network accessline 65
- User prefers tabs for indentation - Default branch is "develop" - API base URL is https://api.oldservice.com/v1 - Network accessline 66
- Default branch is "develop" - API base URL is https://api.oldservice.com/v1 - Yesterday the user mentioned they like dark themes - Network accessline 67
- API base URL is https://api.oldservice.com/v1 - Network accessline 98
- [2025-01-08] Default branch is "develop" (source: session, confidence: high) - [2025-01-05] Deploy target is AWS us-east-1 (source: session, confidence: high) - [2025-01-03] API hosted at https://api.oldservice.com/v1 (source: session, co - Network accessline 99
- [2025-01-05] Deploy target is AWS us-east-1 (source: session, confidence: high) - [2025-01-03] API hosted at https://api.oldservice.com/v1 (source: session, confidence: high) DECEOF - Network accessline 100
- [2025-01-03] API hosted at https://api.oldservice.com/v1 (source: session, confidence: high) - Network accessline 126
cat > "$session2_file" << SESS2EOF {"type":"human","content":"We're moving the API to the new domain. The base URL is now https://api.newplatform.io/v2"} - Network accessline 127
{"type":"human","content":"We're moving the API to the new domain. The base URL is now https://api.newplatform.io/v2"} - Network accessline 128
{"type":"assistant","content":"I'll update all references to use the new API base URL: https://api.newplatform.io/v2"} - Dangerous shell operationline 217
if eval "$1"; then - Dangerous shell operationline 348
rm -rf "$BASE_DIR"
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Declared and executed: 2 facts
- Contacts api.oldservice.com, which SKILL.md, the README and the plugin manifest do not mentiontest-dream.sh:67High confidence
- Contacts api.newplatform.io, which SKILL.md, the README and the plugin manifest do not mentiontest-dream.sh:127High confidence
Signal confidence: 20 facts
- Network access in code of documentationREADME.md:41Low confidence
- Network access in code of documentationREADME.md:47Low confidence
- Dangerous shell operation in code of the SKILL.mdSKILL.md:96High confidence
- Dangerous shell operation in code of the SKILL.mdSKILL.md:360High confidence
- Executable script in code of a file that runsdream-hook.sh:1High confidence
- Executable script in code of a file that runsinstall.sh:1High confidence
- Dangerous shell operation in code of a file that runsinstall.sh:119High confidence
- Executable script in code of a file that runsshould-dream.sh:1High confidence
- Executable script in code of a file that runstest-dream.sh:1High confidence
- Network access in code of a file that runstest-dream.sh:65High confidence
- Network access in code of a file that runstest-dream.sh:66High confidence
- Network access in code of a file that runstest-dream.sh:67High confidence
- Network access in code of a file that runstest-dream.sh:98High confidence
- Network access in code of a file that runstest-dream.sh:99High confidence
- Network access in code of a file that runstest-dream.sh:100High confidence
- Network access in code of a file that runstest-dream.sh:126High confidence
- Network access in code of a file that runstest-dream.sh:127High confidence
- Network access in code of a file that runstest-dream.sh:128High confidence
- Dangerous shell operation in code of a file that runstest-dream.sh:217High confidence
- Dangerous shell operation in code of a file that runstest-dream.sh:348High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
