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 agentmods add skills/infohata/mind-vault/compoundnpx skills add infohata/mind-vault --skill compoundgit clone --depth 1 https://github.com/infohata/mind-vaultWrote 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/infohata/mind-vault/compound)<a href="https://agentmods.dev/skills/infohata/mind-vault/compound"><img src="https://agentmods.dev/badge/skills/infohata/mind-vault/compound.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 | $0.00085 | $0.06268 |
| Opus 5 | $0.00043 | $0.03134 |
| Sonnet 5 | $0.00017 | $0.01254 |
| Haiku 4.5 | $0.00009 | $0.00627 |
Grade A, and why
compound 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 yesterday.
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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
compound
Fifth and final stage of the five-stage sprint workflow (idea → brainstorm/plan → work → review → compound). The novel piece of the workflow and its entire point: every solved problem becomes a candidate for promotion into mind-vault, compounding the knowledge store so the next project (or the next sprint on the same project) starts with a higher floor.
CE's compound writes project-local only. Mind-vault's compound routes to six destinations because mind-vault is the cross-project knowledge store — the routing surface is the whole value.
This skill never commits to main and never merges a PR. It stages, commits to feature branches, pushes, and maintains open PRs per RULE_git-safety.
When to use
TRIGGER when:
- user says "compound this", "let's capture what we learned", "document this fix", "promote this to mind-vault", "write this up", "save this learning"
- a review loop (
/review-loop) just cleared findings and there's a non-trivial lesson worth preserving — the review output file is a first-class input source (seereferences/review-finding-ingest.md) - a bug was just fixed and the root cause is non-obvious / recurring / cross-project
- a pattern that kept coming up across multiple tasks finally got named
SKIP when:
- the fix is trivial and the "lesson" is just "I wrote the code" — nothing to compound
- you're mid-implementation (this is a post-incident skill, not a learning ledger)
- the user wants to capture a new improvement idea — that's
/idea, not/compound
Pattern
1. Collect the raw learning
Accept input in this order of preference:
- Explicit prompt content in the skill invocation (
/compound the HMAC flat-payload trap). - Review-loop output file at
<project>/.bugbot-loop/<run-id>/findings.mdor<project>/.copilot-loop/<run-id>/findings.md(or wherever the loop writes its artifact) when recent. Seereferences/review-finding-ingest.mdfor parsing rules — each cleared finding becomes a candidate compound entry. Engine-agnostic: same parsing rules apply to either bot's output. - PR comment thread when the user points at one (
/compound pr:123#comment-456). - Interactive prompt when nothing is supplied: "What did you learn? Give me the one-sentence essence first, then we'll expand."
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed 5bed9481e92e
- 5d ago First seen · 227 lines · 85 tokens per session scan A 32bd1fb2de19
compound is a skill published in the GitHub repository infohata/mind-vault (2 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 6,268 once invoked, about $0.0004 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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…