Borrowing it
Nothing to install: this file belongs to victoriacity/openakari. 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/victoriacity/openakari/main/.claude/skills/compound/SKILL.mdgit clone --depth 1 https://github.com/victoriacity/openakariWrote 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/victoriacity/openakari/compound)<a href="https://agentmods.dev/skills/victoriacity/openakari/compound"><img src="https://agentmods.dev/badge/skills/victoriacity/openakari/compound/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/victoriacity/openakari/compound"><img src="https://agentmods.dev/badge/skills/victoriacity/openakari/compound.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 | $0.00026 | $0.04430 |
| Opus 5.5 | $0.00010 | $0.01772 |
| Sonnet 5.5 | $0.00005 | $0.00886 |
| Haiku 4.5 | $0.00003 | $0.00443 |
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 2mo 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/compound [mode]
Compound engineering phase — turns session work into accumulated system advantage by embedding learnings into conventions, skills, and patterns. Invoked as Step 5 of autonomous work cycle SOP.
Tier selection
/compound fast— 1-2 turns, skip cross-session scanning/compound deep— 10-15 min, full procedure with deep-mode scope/compound(no argument) — auto-detect: scheduler injects directive to use fast if full ran <3h ago; otherwise run full
Rationale: 83% of sessions produce zero compound actions. Fast saves ~$5.40/day by skipping redundant cross-session scans. See projects/akari/analysis/compound-step-overhead-analysis.md.
Fast compound
Step 1: Review session work
Run !git diff --stat HEAD~N..HEAD. Identify what changed.
Step 2: Check for session learnings
Ask the 4 questions from Step 2: non-obvious facts, failure modes, useful techniques, convention friction.
Step 3: Quick task discovery
If completed experiment/analysis, check EXPERIMENT.md Findings for: unresolved questions, failed criteria, "N too small", multi-phase gaps. Create task with provenance if found.
Step 4: Fleet output spot-check
Read last 5 fleet sessions from .scheduler/metrics/sessions.jsonl (entries with "triggerSource":"fleet"). Check: verification pass rate, any 0-commit or 0-turn sessions. Report: "Fleet: N/M passed" or "Fleet: no recent sessions."
Step 5: Act on learnings
Apply small updates directly. Larger changes → task. See Step 10 for growth accounting and 400-line gate.
Output (fast)
Compound (fast): N actions — <summary>. or Compound (fast): no actions.
Skip cross-session scanning — covered by full compound.
Pre-compound commit: Check git status. Commit uncommitted session work first.
Full compound
The standard compound procedure. Runs when auto-detection determines a full scan is needed (~2-5 minutes), or when explicitly requested without the fast argument.
Background
Compound engineering turns individual session work into accumulated system advantage. The compound phase embeds learnings from each task into conventions, skills, and patterns — transforming linear progress into exponential improvement. See projects/akari/analysis/ralph-loop-architecture-analysis.md for the underlying pattern.
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.
- 2mo ago First seen · 370 lines · 26 tokens per session scan A 1583fcced950
compound is a skill published in the GitHub repository victoriacity/openakari (47 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 4,430 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, source notes, 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…
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…
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…
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…