How do I install the Gotcontext Memory Streaming Digests skill?

Run npx skillmds@latest add oimiragieo/gotcontext-memory-streaming-digests-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Gotcontext Memory Streaming Digests safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Gotcontext Memory Streaming Digests?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Gotcontext Memory Streaming Digests free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Gotcontext Memory Streaming Digests?

oimiragieo (@oimiragieo) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Gotcontext Memory Streaming Digests by oimiragieo

Name: Gotcontext Memory Streaming Digests
Author: oimiragieo

Gotcontext Memory Streaming Digests

Use when dreaming over multi-GB transcript corpora, fixing OOM / heap pressure, implementing or auditing SessionDigest streaming, stratified max-sessions windows, concurrent digestion, distinguishing truncated from malformed reads, or Cursor .vscdb vs *.jsonl dream wiring in gotcontext-memory.

oimiragieo Updated Sep 21, 2026 0 repo stars

File contents

gotcontext-memory — streaming digests

Companion to gotcontext-memory-hitl-honesty. Load when the problem is scale, not HITL policy.

Why this exists

Measured corpus: ~9.6 GB / 11k+ Claude transcripts, including a ~2.3 GB file that readFile rejects (> 2 GiB). Accumulating full Transcript[] cannot work. Dream must stream into bounded digests and reason only over digests.

Rules

Stream, don’t slurp — digestTranscriptFile / digestRoots in src/dream/digest.ts.
Truncated ≠ malformed — byte ceiling → truncated: true; parse/unreadable → malformed.
Counts vs samples — DIGEST_SIGNAL_CAP bounds arrays; counts always increment.
Stratified window — --max-sessions (default 400) via selectDigests: ≈2/3 newest + evenly sampled older strata (session clock). Newest-N alone collapses calendar span.
Concurrent digestion — bounded worker pool (default 8); modest I/O-bound speedup.
.vscdb on the path — enumerate with *.jsonl; digestVscdbFile + shared classifyText (BL-DRM-016 closed 2026-08-10). Unreadable .vscdb → malformed, not fatal.
Prove on real size — oversized / truncated fixtures before claiming “works.”

Do not

Reintroduce whole-file readFile for dream corpus.
Report only malformed when the failure was a size ceiling.
Re-open a silent harness drop without HONESTY + backlog.

Authority

Lessons L15, L18, L22 — docs/LESSONS_2026-08-09.md
docs/HONESTY.md, docs/features/dream.md, docs/guides/rebuild-from-scratch.md
Tests: test/digest.test.ts, test/digest-vscdb.test.ts, test/digest-window.test.ts

Verify

cd gotcontext-memory && npm test -- test/digest.test.ts test/digest-vscdb.test.ts test/digest-window.test.ts

---name: gotcontext-memory-streaming-digests-2description: Use when dreaming over multi-GB transcript corpora, fixing OOM / heap pressure, implementing or auditing SessionDigest streaming, stratified max-sessions windows, concurrent digestion, distinguishing truncated from malformed reads, or Cursor .vscdb vs *.jsonl dream wiring in gotcontext-memory.---# gotcontext-memory — streaming digestsCompanion to `gotcontext-memory-hitl-honesty`. Load when the problem is **scale**, not HITL policy.## Why this existsMeasured corpus: **~9.6 GB / 11k+ Claude transcripts**, including a **~2.3 GB** file that`readFile` rejects (`> 2 GiB`). Accumulating full `Transcript[]` cannot work. Dream muststream into bounded digests and reason only over digests.## Rules1. **Stream, don’t slurp** — `digestTranscriptFile` / `digestRoots` in `src/dream/digest.ts`.2. **Truncated ≠ malformed** — byte ceiling → `truncated: true`; parse/unreadable → `malformed`.3. **Counts vs samples** — `DIGEST_SIGNAL_CAP` bounds arrays; counts always increment.4. **Stratified window** — `--max-sessions` (default 400) via `selectDigests`: ≈2/3 newest + evenly sampled older strata (session clock). Newest-N alone collapses calendar span.5. **Concurrent digestion** — bounded worker pool (default 8); modest I/O-bound speedup.6. **`.vscdb` on the path** — enumerate with `*.jsonl`; `digestVscdbFile` + shared `classifyText` (BL-DRM-016 **closed** 2026-08-10). Unreadable `.vscdb` → malformed, not fatal.7. **Prove on real size** — oversized / truncated fixtures before claiming “works.”## Do not- Reintroduce whole-file `readFile` for dream corpus. - Report only `malformed` when the failure was a size ceiling. - Re-open a silent harness drop without HONESTY + backlog.## Authority- Lessons **L15**, **L18**, **L22** — `docs/LESSONS_2026-08-09.md` - `docs/HONESTY.md`, `docs/features/dream.md`, `docs/guides/rebuild-from-scratch.md` - Tests: `test/digest.test.ts`, `test/digest-vscdb.test.ts`, `test/digest-window.test.ts`## Verify```bashcd gotcontext-memory && npm test -- test/digest.test.ts test/digest-vscdb.test.ts test/digest-window.test.ts```

Frequently asked questions