agentleFS
wrg32786wrg32786/aigent-os/skills/dream/SKILL.md

dream

Skill25 starsChanged 7 days agoMITView on GitHub

Synthesize lessons and propose improvements from recent operating evidence. Use when reviewing sessions, consolidating notes, or finding patterns.

40 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ingest, init and 8 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.
  • JaimeGBASkill

    ingest

    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

  • MicrosoftSkill

    init

    Also in 4 projects that use this

  • Hugging FaceSkill

    simplify

    Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.

    Also in 3 projects that use this

  • SentrySkill

    deslop

    Strip AI-generated noise from the diff before pushing — extra comments a human wouldn't write, defensive try/catch in trusted code paths, casts to any, inline imports in Python, and other style inconsistencies with the surrounding file. Use this immediately before commit so the diff stays clean.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    reflect

    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

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 39 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When evidence names a repeatable system gap, append this inside the same dated Dream section:

    line 92
  2. Distinctive:

    Never overwrite an earlier entry.

    line 125
  3. Very specific:

    Only DREAM_CONTRACT PASS is green.

    line 144

“Common” is measured: kept by at least 6 in 10 of the 39 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/dream - evidence-gated synthesis

/dream is the canonical writer for lessons and Dream synthesis. It never applies an improvement, promotes its own proposal, edits system instructions, or treats an agent-authored claim as verification.

Canonical ownership

  • Lessons: vault/memory/runtime/LESSONS.jsonl.
  • Dream synthesis: vault/memory/DREAM_LOG.md.
  • The documented memory/ fallback is valid only for minimal installations.
  • Any older runtime/DREAM_LOG.md copy is not an input or output.
  • /close and /nightly invoke this protocol instead of carrying a competing inline writer.
  • Candidate status transitions also go through this writer.

Invocation

/dream
/dream --window nightly
/dream --set-status <candidate-id> <approved|merged|rejected|blocked> \
  --operator-evidence "<direct operator reference>"

proposed -> approved always requires the operator's exact decision. Never infer approval from silence, an automated status, another agent, or prior prose.

Sources

Read, in order:

  1. The newest five valid capsules by frontmatter created_at.
  2. The newest five dated live Session Log blocks.
  3. Open Trust Decay captures.
  4. The newest three dated Honesty Ledger sessions.
  5. Recent Failed Experiments and Failure Modes entries.
  6. Existing Lessons JSONL for dedupe and prior evidence chains.
  7. Staged NIGHTLY_CAPTURE_CANDIDATES.jsonl rows from the prior fire as discovery and pressure signals only.
  8. Explicitly supplied local Git or command evidence.

Record exact source references. A capsule or Session Log entry can establish that a claim occurred; it cannot prove the claim true.

Lesson admission predicate

Append a lesson only when one is true:

  • the same pattern appears in at least two independent source events;
  • one explicit operator directive is paired with a separately observed outcome; or
  • one mechanical red-before/green-after predicate supplies an artifact and literal exit codes.

Two retellings of one event are not independent. Discard one-off observations, unverified causal stories, and self-confirmation.

Each admitted lesson has:

  • lesson_id: next max numeric lNNN suffix plus one;
  • type: procedural | calibration | strategic | failure-mode | doctrine;
  • confidence: 0.0..1.0, capped at 0.85 for one mechanical event;
  • source_events: at least two refs unless an allowed exception applies;
  • created_at: the configured local YYYY-MM-DD;
  • admission: one of:
    • {kind: "two-source"};
    • {kind: "operator-outcome", operator_ref, outcome_ref};
    • {kind: "mechanical-red-green", red_exit, green_exit: 0, artifact_ref}.

Serialize UTF-8 JSON, parse the complete JSONL file after append, and confirm the new line round-trips. Historical duplicate ids do not authorize a new collision.

Improvement candidate predicate

When evidence names a repeatable system gap, append this inside the same dated Dream section:

### ni-YYYYMMDD-NN - short name
- **status:** proposed
- **evidence:** source-ref-1; source-ref-2
- **failure class:** concise class
- **proposed_change:** smallest testable change
- **mutation proof:** break condition -> named red; restore -> named green
- **operator gate:** approve / reject / revise
- **operator evidence:** pending

Generated candidates always start with the literal field status: proposed. Any generated approved, merged, or self-ratifying wording is a hard failure.

Canonical dated entry

Append one ## YYYY-MM-DD (...) section every time synthesis runs, even with zero admitted lessons. It must contain nonempty forms of all eight labels:

  • Sources reviewed
  • Lessons extracted
  • Improvement candidates proposed
  • Patterns observed
  • Discarded as one-off
  • Calibration miscalls
  • Productive surprises
  • Open trust-decay items to watch

A quiet run writes a minimal zero-lesson entry and appends no Lessons row. Never overwrite an earlier entry.

Executable postcondition

A nightly fire uses the snapshot created by nightly-pass begin. Explicit /dream creates an operating-system temp snapshot first:

node daemons/nightly-contracts.mjs snapshot --root <aigent-root> \
  --out <os-temp>/dream-contract-before.json

After writing:

node daemons/nightly-contracts.mjs dream --root <aigent-root> \
  --date <YYYY-MM-DD> --snapshot <os-temp>/dream-contract-before.json

Only DREAM_CONTRACT PASS is green. The validator proves byte-prefix preservation, parses JSONL, derives ids, validates admission, masks fenced examples, requires the eight sections and current configured date, and rejects a newly generated candidate that does not start proposed.

Return:

DREAM PASS date=<YYYY-MM-DD> sources=<N> lessons=<N> candidates=<N>

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.