Command

The rest of this file describes how runs use memory (/archeflow:run calls these steps itself).

Cross-Run Memory

ArcheFlow forgets everything after each run. This skill extracts lessons from completed runs and injects them into future agent prompts, so recurring issues (timeline errors, missing null checks) are caught proactively.

Storage

.archeflow/memory/lessons.jsonl     # Append-only, one lesson per line
.archeflow/memory/archive.jsonl     # Decayed lessons (frequency reached 0)
.archeflow/memory/audit.jsonl       # Injection audit trail

Lesson Types

Lesson JSON Fields

Example:

{"id":"m-001","ts":"2026-04-03T14:00:00Z","run_id":"2026-04-03-add-auth","type":"pattern","source":"guardian","description":"Timeline references must match story start day","frequency":2,"severity":"bug","domain":"writing","tags":["continuity","timeline"],"last_seen_run":"2026-04-03-add-auth","runs_since_last_seen":0}

Auto-Detection

After each run.complete, extract lessons from findings:

<archeflow-root>/lib/archeflow-memory.sh extract .archeflow/events/<run_id>.jsonl

The script reads review.verdict events, matches findings against existing lessons by keyword overlap (50%+ threshold), increments frequency on matches, and creates new candidate lessons (frequency: 1) for unmatched findings with severity >= WARNING.

Promotion rule: A finding needs frequency >= 2 (seen in 2+ runs) before injection. This filters out one-off noise. Preferences skip this threshold.

Injection

Before spawning agents, inject relevant lessons:

<archeflow-root>/lib/archeflow-memory.sh inject <domain> <archetype>

Rules: filters by domain (or general), optionally by archetype, requires frequency >= 2, sorts by frequency descending, caps at 10 lessons. Lessons with frequency >= 5 are always injected regardless of filters.

Injected as a markdown section appended to the agent's system prompt:

## Known Issues (from past runs)
- Timeline references must match story start day [seen 3x, guardian]
- Voice drift common in monologue passages >200 words [seen 2x, sage]

Decay

After each run.complete, apply decay: lessons not seen for 10 runs lose 1 frequency. When frequency reaches 0, the lesson is archived.

<archeflow-root>/lib/archeflow-memory.sh decay

Manual Management

See the Command table at the top. Lessons added by hand are type preference and are injected from the next run on.

Audit Trail

Track which lessons are injected per run and whether they were effective. Pass --audit <run_id> to inject to log records. After a run, audit-check <run_id> compares injected lessons against review findings: no matching finding = helpful (issue prevented), matching finding = ineffective (issue repeated despite injection).

<archeflow-root>/lib/archeflow-memory.sh inject <domain> "" --audit <run_id>
<archeflow-root>/lib/archeflow-memory.sh audit-check <run_id>

Integration Points