dreamer-run
Skill2 starsChanged 5 months agoMITView on GitHub
Run the Forge Dreamer — a nightly lesson consolidation daemon
In this repository46 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- forge-opencode/CLAUDE.mdCLAUDE.md
- forge-adoptSkill
- forge-arch-proSkill
- forge-archSkill
- forge-autopilotSkill
- forge-autopilot-stopSkill
- forge-build-proSkill
- forge-buildSkill
- forge-deploySkill
- forge-doctorSkill
- forge-evalSkill
- forge-feedbackSkill
- flowSkill
- forge-force-advanceSkill
- graduateSkill
- health-checkSkill
- forge-initSkill
- forge-monitorSkill
- forge-orchestrateSkill
- forge-plan-proSkill
- forge-planSkill
- preflightSkill
- forge-product-proSkill
- forge-productSkill
- forge-releaseSkill
- forge-resolveSkill
- forge-resumeSkill
- forge-retroSkill
- forge-reviewSkill
- forge-rulesSkill
- forge-set-profileSkill
- skill-creatorSkill
- forge-spec-proSkill
- forge-specSkill
- forge-sprint-proSkill
- forge-sprintSkill
- forge-srs-proSkill
- forge-srsSkill
- forge-statusSkill
- forge-trace-matrixSkill
- forge-uninstallSkill
- forge-validateSkill
- watchSkill
- watch-stopSkill
- forge-whySkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
Run the Dreamer consolidation pass:
≈ “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
Forge Dreamer Run — lesson consolidation
Runs the Dreamer daemon (REQ-F-015..021). Idempotent: running /forge:dreamer-run
twice the same day produces the same digest. The Dreamer reuses a single claude -p
session (resumed each run) pinned to a cheap model for the optional consolidation
step, and writes the daily digest to pipeline/log/.
When to Use
- User types
/forge:dreamer-runor asks to consolidate lessons, run lesson decay, check for duplicate or contradicting lessons, or produce a daily digest. - As a nightly/scheduled step after a batch of new lessons have been synced.
When NOT to Use
- The user wants to view the latest digest directly — read
pipeline/log/daily-<date>.md. - The user wants to edit or delete lessons — Dreamer flags only, never mutates decisions.
Steps
- Run the Dreamer consolidation pass:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/dreamer.py --run --cwd "$(pwd)" - Present the results to the user:
- Decayed: N lessons moved to dormant (confidence below threshold).
- Duplicate pairs: N pairs flagged (Jaccard ≥ 0.8 on trigger+rule word-sets).
- Contradiction pairs: N pairs flagged (similar trigger, opposing rule polarity).
- Digest: path to
pipeline/log/daily-<date>.md. - Consolidation: whether a background summary was generated.
- Remind the user:
- Duplicate and contradiction pairs are flags only — the Dreamer never merges or resolves them automatically. Review the digest and decide manually.
- The digest is at
pipeline/log/daily-<date>.mdand can be read any time.
Verification
pipeline/log/daily-<date>.mdexists and contains today's date after a successful run.- Re-running
/forge:dreamer-runthe same day produces the same digest content (no duplication, no appending).
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.

