dream
Skill2 starsChanged 5 months agoMITView on GitHub
Scheduled memory maintenance for Engram — verify the highest rot-risk memories, confirm the ones that still hold, and supersede the ones reality has moved past. Maintenance only; never summarizes or merges memories. Runs safely as a dry-run by default; pass `--apply` to write changes. Intended to run nightly via /schedule.
41 other projects use a version of this.
Adopted by
Most recently taken up by
- srinator22/agent-kerneltheir own version, first seen Nov 15, 2026
- fjwood69/moritheir own version, first seen Nov 10, 2026
- srinator22/New-Projecttheir own version, first seen Nov 8, 2026
- Melvynx/ai-maxxing-skillstheir own version, first seen Nov 8, 2026
- alexandrosandre/agentic-engineeringtheir own version, first seen Nov 8, 2026
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
Used with
Projects with it also use ingest, resume and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JaimeGBASkillingest
Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base
Also in 4 projects that use this
genomewalkerSkillresume
Resume a thread by loading its ~800-token context capsule
Also in 3 projects that use this
MicrosoftSkillinit
Also in 4 projects that use this
Hugging FaceSkillsimplify
Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.
Also in 3 projects that use this
AnthropicSkillstart
Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.
Also in 3 projects that use this
Microsoft AzureSkillreflect
Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.
Also in 3 projects that use this
Other versions41 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 41
- Noizefield/audio-plugin-coder★ 334same name
- grandamenium/dream-skill★ 136same name
- sneg55/agent-starter★ 76same name
- oprogramadorreal/optimus-claude★ 75same name
- tranhieutt/software_development_department★ 71same name
- Melvynx/ai-maxxing-skills★ 46same name
- maxvaega/awesome-skills★ 40same name
- seldonframe/seldonframe★ 40same name
- hyperb1iss/hyperskills★ 36same name
- fjwood69/mori★ 32same name
31 more not listed
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 repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- deslopSkill
- queueSkill
- self-reflectionSkill
- workSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 40 edited versions we read keep these.
1
Distinctive
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
- could be automatic: a setting could enforce it
- Very specific: line 29
If you can determine the corrected fact from the repo, in --apply mode supersede it: engram supersede <id> "<corrected markdown fact>" …
- Distinctive: line 50
Always end with a digest (printed, never stored as a memory):
- Very specific: line 64
Maintenance only: Never rewrite a memory into a summary, never merge or cluster memories.
- Very specific: line 70
Run nightly via /schedule (e.g.
“Common” is measured: kept by at least 6 in 10 of the 40 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Maintain the Engram memory store: surface and fix rot, without ever
summarizing or clustering memories (that is what slopped the prior system —
see ADR 0008). Default is a dry-run that mutates nothing and just reports;
only --apply writes changes.
1. Pull the riskiest candidates
engram list --by-risk --limit ${LIMIT:-20} --jsonRot-risk already excludes userConfirmOnly/timeless (they score 0), so you
only see machine-checkable memories.
2. Deterministic verdicts first (cheap, no LLM)
engram verify --jsonMatch verdicts to the candidates by id. Verdicts: confirmed | contradicted | stale | inconclusive.
3. Act on each candidate
- confirmed → it still holds. In
--applymode:engram verified <id>(bumpsverified_at, lowers its future risk). - contradicted (e.g. the
checkAnchorfile is gone) → reality moved.- If you can determine the corrected fact from the repo, in
--applymode supersede it:engram supersede <id> "<corrected markdown fact>" --reason "<what changed>" --tags <tags> --source <repo>. - High-certainty contradiction with no replacement — the
checkAnchoris gone AND the thing the memory describes no longer exists, so there's nothing to supersede it with: in--applymode soft-delete it withengram delete <id>. This is the ONLY case/dreamdeletes, anddeleteis a recoverable tombstone (the row is kept), so it's safe. If you're unsure whether a replacement exists → do NOT delete; digest it. - Otherwise (fix unclear) → add to the review digest (don't guess).
- If you can determine the corrected fact from the repo, in
- stale (old
as of <date>) → treat like contradicted: supersede if you can refresh it, else digest it. - inconclusive → escalate to a subagent (see §4) only if it has a
checkAnchor; otherwise leave it and digest it.
4. Escalate inconclusive by FALSIFICATION
For each inconclusive memory with a checkAnchor, spawn a subagent (Task)
whose job is to disprove the memory — not confirm it. Give it the memory
content + checkAnchor + its source repo, and instruct: "Find concrete
evidence this is now FALSE (run the checkAnchor grep/command, read the file).
Report DISPROVED + the corrected fact, CONFIRMED + the evidence, or UNKNOWN."
- DISPROVED → (
--apply)engram supersedewith the corrected fact. - CONFIRMED → (
--apply)engram verified <id>. - UNKNOWN → leave it; add to the digest.
A falsification prompt resists the rubber-stamping a "prove it's still true" prompt invites.
5. Report a digest
Always end with a digest (printed, never stored as a memory):
- confirmed/re-verified: N
- superseded: N (old → new, with reason)
- soft-deleted (high-certainty contradiction, recoverable): N
- needs your review — for each memory that couldn't be auto-resolved, show its
verdict + why and offer the three actions: keep (it's still fine — I'll
engram verifiedit), update (give me the new fact — I'llengram supersede), or drop (engram delete, recoverable). Nothing in this list is touched until you choose.
In dry-run (the default) the digest describes what would happen; nothing is
written. Tell the user to re-run with --apply to enact it.
Hard rules
- Maintenance only. Never rewrite a memory into a summary, never merge or
cluster memories. The only writes are
engram verifiedandengram supersede. - Supersede, don't delete. History is preserved via
superseded_by+evolution_reason. - Operate on the shared store (no
--env).
Scheduling
Run nightly via /schedule (e.g. a routine that invokes /dream --apply at a
quiet hour). Start with dry-run runs until you trust its supersede decisions.
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.

