The Remembrall

---
name: the-remembrall
description: Mine the repo's own session transcripts for places the human corrected the agent, cluster them, and derive which instruction is missing, wrong, or being ignored — the evidence-first inverse of every other pass, which read text and reason about it. Use for "what do I keep having to tell it", "why does it ignore that rule", "what belongs in my memory file that isn't there", "which of my rules has never once mattered", or as part of /opus-pocus. Reads local transcripts in place, quotes minimally, transmits nothing. Reports could-not-verify when no transcript store exists. NOT for auditing the instruction text itself (→ clarificus-maxima and the other text passes). NOT for measuring whether a landed fix worked (→ the-pensieve).
---

# 🔮 The Remembrall

> *"It glows when you've forgotten something. You forgot to write it down."*

Every other spell in this book reads the instruction layer and reasons about it. This one reads
what actually happened. When a human corrects an agent, that correction is ground truth about a
missing or broken instruction — and no amount of re-reading the memory file will produce it,
because the file's whole defect is that the thing isn't in it. Corrections are the cheapest
evidence a repo already has and never looks at.

The book's own doctrine says verify the artifact, never the call. The artifact here is the
transcript.

## What to scan

Session transcripts, in place. On Claude Code these are JSONL under
`~/.claude/projects/<url-encoded-cwd>/*.jsonl` — the path is undocumented and version-specific,
so **confirm it before promising anything**:

```sh
ls ~/.claude/projects/*/ 2>/dev/null | head
```

If the store is absent, unreadable, or holds fewer than a handful of sessions, this pass reports
`? — could not verify`. That is a distinct verdict from a clean one: no transcripts means nothing
was examined, not that nothing is wrong.

Alongside them, the resolved memory files and rule files — not to audit their prose, but to answer
one question per finding: *is this correction already written down somewhere?*

**Privacy.** Transcripts are the user's own local data and often contain far more than this pass
needs. Read them in place, quote the minimum that makes a finding checkable, and transmit nothing
anywhere. If a correction cannot be quoted without dragging in unrelated content, describe it and
cite the line rather than pasting it.

## Anti-patterns to find

1. **Repeated correction.** The human said substantially the same thing three or more times
   across sessions, and it appears in no instruction file. The rule already exists — it lives in
   the human's fingers instead of the repo. Its wording is already dictated by the corrections.
2. **Ignored instruction.** A rule exists and the transcripts show the agent violating it anyway.
   This is the highest-value class and the most often misdiagnosed: the fix is almost never
   "state it more forcefully". Diagnose *why* first — the rule is unfindable (in a file nothing
   loads at the moment it matters), out-scoped (its trigger never matches the real situation), or
   outranked (a louder rule nearby wins every collision).
3. **Never-triggered instruction.** A rule whose trigger situation has not occurred once in
   recorded history. Untriggered text is untested text. Do not delete it here — hand it to
   `avada-verbosa`, which names this candidate class and has no way to mine it.
4. **Workflow fiction.** Instructions describing a process the transcripts show nobody follows —
   a documented route that is always taken differently, a ritual described in the file and absent
   from every session. Either the workflow moved and the file didn't, or the workflow was
   aspirational from the start.
5. **Correction cluster with no rule.** A topic the human keeps steering, in different words each
   time, with no single repeated phrase to match on. Harder to detect than class 1 and worth more:
   it is a missing rule whose scope the human has been drawing by hand, one session at a time.
6. **Correction reversal.** The human corrected the agent toward X in one session and toward
   not-X later. Either the intent changed and the file records the old one, or two situations look
   alike and need distinguishing. Never propose a rule from one half of a reversal without saying
   the other half exists.

## Fix prescriptions

| Finding class | Fix |
|---|---|
| Repeated correction | Propose the instruction **in the human's own words from the transcript**, cited. They already found the phrasing that works; rewriting it into house style is how the meaning drifts |
| Ignored instruction | Diagnose before rewording. Unfindable → move it where it loads when it matters (a path-scoped rule, the folder's own file). Out-scoped → fix the trigger. Outranked → the collision is a `contradicto-revelio` finding; hand it over rather than shouting louder |
| Never-triggered | Hand to `avada-verbosa` as a candidate with its evidence (searched N sessions, zero occurrences). This pass supplies the mining; that pass owns the removal and its baseline |
| Workflow fiction | Establish which is true — the file or the sessions — and change the loser. A file describing a workflow nobody runs is worse than silence, because it is confidently wrong |
| Cluster with no rule | Propose the scope the corrections actually draw, quoting two or three of them so the reader can check the boundary you inferred |
| Reversal | Report both sides and ask which is current. This is a genuine requirement question, not something to resolve by picking the more recent one |

## Bounds

- Scope: the transcript store for **this repo**, plus the resolved memory and rule files for the "is it written down?" check. Not other projects' transcripts, not application source, not another installed plugin's artifacts.
- Cap: at most 15 findings, ranked by how often the correction recurred. Sample rather than exhaust — the most recent 30–50 sessions answer this well, and reading a year of history to find one more instance is the unbounded sweep this book bounds.
- Done when the sampled window has been read once and the clusters ranked. Not when corrections stop appearing; on a real project they never do.
- Quote once, at read time, and minimally; mark anything you cannot re-confirm `UNVERIFIED` rather than re-reading to check yourself.
- Read-only, and local-only: no transcript content leaves the machine.
- See `skills/opus-pocus/references/casting-safety.md` for the full rules.

## Report format

Lead with the denominator: sessions available, sessions read, date range. Then per finding:
class (1–6) · the correction quoted minimally with its session and line · how many times it
recurred · whether an instruction already covers it (and where) · the prescription. Rank by
recurrence count, not by how interesting the topic is.

`? — could not verify` when no transcript store was found or it was unreadable — never a clean
grade. `SCANNED NOTHING` if the store exists but held no sessions for this repo.