Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add randomm/pi-ensemble --skill vipunegit clone --depth 1 https://github.com/randomm/pi-ensembleWrote 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/randomm/pi-ensemble/vipune)<a href="https://agentmods.dev/skills/randomm/pi-ensemble/vipune"><img src="https://agentmods.dev/badge/skills/randomm/pi-ensemble/vipune/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/randomm/pi-ensemble/vipune"><img src="https://agentmods.dev/badge/skills/randomm/pi-ensemble/vipune.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00191 | $0.04618 |
| Opus 5.5 | $0.00076 | $0.01847 |
| Sonnet 5.5 | $0.00038 | $0.00924 |
| Haiku 4.5 | $0.00019 | $0.00462 |
Grade A, and why
vipune 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 1mo 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vipune memory skill (pi-ensemble bundled)
Source-of-truth note. This is pi-ensemble's project-bundled vipune doctrine. It was originally adapted from a personal Claude Code skill, but the bundled version is the canonical reference for pi-ensemble going forward. The role-sized derivative modules at
modules/core/vipune-{light,baseline,heavy}.mdare proper subsets of this skill — when they diverge, the skill is right and the modules need a resync. See the procedure-type memory"sync pi-ensemble vipune modules"for the workflow.
Vipune is a CLI semantic memory store with project scoping, hybrid search, and typed memories — the authoritative persistent memory layer for every pi-ensemble session.
Codebases evolve, conventions accumulate, the user corrects the agent on things, and constraints get discovered together. None of that should be re-learned session by session. Vipune is the durable layer that prevents repeating mistakes and re-paving ground already walked.
The mandate: search vipune at the start of every task, save vipune memories at task boundaries. This is not optional. It is the protocol.
Why vipune over file-based notes
- Semantic search finds memories by meaning, not exact keywords
- Project scoping is automatic via git remote — no cross-contamination between codebases
- Typed memories route by purpose (fact / preference / procedure / guard / observation)
- Conflict detection at 0.85 similarity flags duplicate memories before write
- Supersede atomically replaces outdated memories — no orphaned contradictions
- Status field (active/candidate) gives a long-term/short-term split
- Recency-weighted search gives implicit decay without losing data
- Single binary, local SQLite — no API calls, no external service, no network dep
- All session agents share the project DB — observations stored by
@exploreor@developerduring a /work cycle are immediately retrievable by PM and other subagents in the same session.
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.
- 1mo ago First seen · 372 lines · 191 tokens per session scan A ae6fec692831
vipune is a skill published in the GitHub repository randomm/pi-ensemble (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 191 tokens to every session and 4,618 once invoked, about $0.0008 per session on Opus 5.5. 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
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…