Borrowing it
Nothing to install: this file belongs to binary16labs/prime-silo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/binary16labs/prime-silo/main/.claude/skills/longview-pipeline/SKILL.mdgit clone --depth 1 https://github.com/binary16labs/prime-siloWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/binary16labs/prime-silo/longview-pipeline)<a href="https://agentmods.dev/skills/binary16labs/prime-silo/longview-pipeline"><img src="https://agentmods.dev/badge/skills/binary16labs/prime-silo/longview-pipeline.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.03308 |
| Opus 5 | $0.00027 | $0.01654 |
| Sonnet 5 | $0.00011 | $0.00662 |
| Haiku 4.5 | $0.00005 | $0.00331 |
Grade A, and why
longview-pipeline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LONGVIEW pipeline — operational knowledge
LONGVIEW map-reduces months of agent sessions (memo-ray store) into per-session cards via a local
model, then graph + themes + report/book/PDF/audiobook.
Pipeline: inventory → extract → map(walk) → (model or graph) → code → weave → enrich → review → reduce(TIMELINE) → opus → pdf.
Code: scripts/longview/. Guide: runtime/docs/operations/LONGVIEW_GUIDE.md.
Governance & observability (v1.16.x) — all deterministic, ledger-sourced:
- Memory teleport (
memory.mjs+memory_graph.py): label→resolve→teleport sensitive sessions (CV/job) to a quarantine workspace (moves files + Neo4j nodes + Chroma chunks, journalled, reversible viarestore);quarantine.jsonfilters teleported sids from inventory forever;lib/leak_gate.mjsgates deliverables. Graph Source names use the 8-char sid prefix, not the 32-char card filename. UI::8788/memory.html. - Dashboard (
scratch/longview_run/dashboard/,bash dash.sh→:8788): Mission Control (/) + Lineage/governance (/lineage.html, OpenLineage DAG + artifact explorer + step-through reusinglib/record.mjs+ execution register) +/kindle.html(ES5). Every number derives fromledger.jsonl+ disk — no hidden state. - Arc-driven opus (
lib/arcs.mjs): timeline-walked cross-project arcs feed sections;draft → gate → critique → revise.LONGVIEW_OPUS_DIR=iterations/<name>builds without clobbering a prior book. - Coverage gotcha:
.meta.jsonalso ends in.json— alwaysfilter(f=>f.endsWith('.json') && !f.endsWith('.meta.json'))or card counts / coverage denominators double. - Ingest wedge fix: server-side
deep_synthesisingest kept flooding the LM host after client death —POST /api/rag/ingest/cancel+GET /api/rag/ingest/active+ a 3-strike connectivity circuit breaker.subprocessEnv()forwards repo.envto spawned python (else LM endpoints unseen).reasoning_effort:"none"+ empty-content→reasoning_contentfallback (post-restart LM Studio diverts the whole reply into reasoning).
Model is env/profile-driven (not hardcoded): BENNY_DEFAULT_MODEL / LONGVIEW_MODEL pick it,
the manifest carries only a preconfigured default. Verified LAN setup: LM Studio on
192.168.68.125:1234 serving lmstudio/google/gemma-4-12b (a reasoning model — the per-call token
budget must clear its ~500-1000-tok preamble, e.g. LONGVIEW_FRAGMENT_MAX_TOKENS=1800, or content
comes back empty → blank cards; full org/model id required; response_format must be json_schema|text,
never json_object). A wedged gemma engine returns HTTP 200 but zero tokens — reload the model on the
LM host to reset it; embeddings on the same host still answering isolates it as generation-specific.
Don't confuse the two empty-content causes (bit us again 2026-07-27, twice): a small-max_tokens
probe (e.g. 16) on this reasoning model returns content:"" + finish_reason:"length" because the
preamble ate the whole budget — that is NOT a wedge. A real wedge = zero completion tokens / no bytes
with a GENEROUS budget. Before declaring a wedge, re-probe with reasoning_effort:"none" OR
max_tokens≥600 and check reasoning_content; only zero-token-under-ample-budget is the engine wedge.
Also: the 12B loads slowly on the eGPU (~35s, ~22 tok/s) — a slow first token is not a hang.
Graph build — two paths, same schema (Source/Concept/RELATES_TO/SOURCED_FROM):
model= deep_synthesis: a second LLM pass re-extracts triples per card section. ~60-120s/card.graph= longview_v2, deterministic: builds triples directly from the card's ownconcepts[]/applications[]/capabilities[]/skills_observed[]— no model call, ~0.4s/card.(:Project)-[INVOLVES/USES/DEMONSTRATES/APPLIES]->entities + an anchorCO_OCCURS_WITHstar per card. The map phase already distilled the entities once, so re-extraction is redundant —graphis the speed lever. Then runenrichto merge duplicate concepts across cards into shared hubs. Code:lib/card_triples.mjs(purebuildCardTriples), server routePOST /rag/graph-upsert(→save_knowledge_triples, no clustering), live earned-ETA vialib/eta.mjs→<ws>/longview/progress.json. Sentence-shaped fields (decisions/outcomes/failures) are deliberately NOT nodes — they stay in the card md for vectors. Blank cards (no entities) are counted + skipped, never written as empty hubs.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 134 lines · 54 tokens per session scan A bbe07f07f98b
longview-pipeline is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 3,308 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
memory-hygiene
Guidelines for writing and consolidating memories effectively in YodMCP.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
learn
Manually record an insight, correction, preference, or rule that the agent should remember for future tasks.
memory-kit
Create a workspace-local .cowork/ memory kit (rules, identity, long-term notes, daily logs, heartbeat templates).
tma1-peer
List recent sessions on this project by agent — peers (Claude Code, OpenClaw, Copilot CLI) or your own past sessions. Invoke this skill when the user asks you to read another agent's review feedback, see what someone else tried, act on cross-agent context, or recall your own earlier work here. Trigger phrases: "what…