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 agents/szara7678/openakashic/distributed-agent-memory-contractgit clone --depth 1 https://github.com/szara7678/OpenAkashicWrote 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/agents/szara7678/openakashic/distributed-agent-memory-contract)<a href="https://agentmods.dev/agents/szara7678/openakashic/distributed-agent-memory-contract"><img src="https://agentmods.dev/badge/agents/szara7678/openakashic/distributed-agent-memory-contract.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 | $0.00000 | $0.01114 |
| Opus 5 | $0.00000 | $0.00557 |
| Sonnet 5 | $0.00000 | $0.00223 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
Distributed Agent Memory Contract 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 5d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summary
Remote agents on different servers should use one shared operating pattern: a world-agent shared memory layer from Closed Akashic over MCP, canonical truth from each project repo, and a tiny per-Codex AGENTS.md that points agents back to this server.
Two-Layer Model
- Closed Akashic (
knowledge.openakashic.com/mcp/): shared working-memory layer, operating docs, project indexes, incidents, decisions, playbooks, images. - Core API (
api.openakashic.com): validated public answer layer. claims / capsules. SLM agents query this viasearch_akashic. - project repo
doc/: canonical product and implementation documents.
kind=capsule and kind=claim notes auto-sync to Core API on publication approval. This is the bridge from shared working memory to SLM-queryable knowledge.
Local agent-knowledge clones are no longer part of the default workflow.
Standard Flow
- Verify
CLOSED_AKASHIC_TOKENand MCP access tohttps://knowledge.openakashic.com/mcp/(trailing slash required). - Read [[Codex Central Memory Setup]] and this contract when attaching a new Codex host.
- Open the project index README in Closed Akashic.
- Before implementation:
search_akashicfor validated knowledge first, thensearch_notesfor related Closed Akashic notes. - Read the project repo's canonical docs.
- Do the work in the repo or server.
- Write back one concise linked note or update the existing best container. Distill — never paste raw logs.
Project Routing
- project memory:
personal_vault/projects/<scope>/<project>/... - cross-project reusable memory:
personal_vault/shared/... - operating docs for all agents:
doc/agents/...
Common scopes include personal, company, client, research, and ops, but they are not hard-coded categories.
Each project workspace should have a README.md. Agents may create or revise subfolders through MCP according to the project shape.
Write-Back Contract
- update an existing note when the container is already right
- create a new note only when the new fact deserves its own history
- keep notes short, link-heavy, and reusable
- do not paste whole chat transcripts
- do not duplicate canonical repo docs
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.
- 5d ago First seen · 69 lines · 0 tokens per session scan A 51468cd7e65b
Distributed Agent Memory Contract is an agent published in the GitHub repository szara7678/OpenAkashic (3 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,114 tokens. 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 agents, from other repositories
brain-os-mode
Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…
ingest-jira
Record one Jira issue as an atlassian-issue document in an AKB vault — title/description/resolution/comments quoted verbatim. Fetched live via the Atlassian MCP server; always upsert.
ingest-pr
Record a single GitHub PR merge event as a git-pr document in an AKB vault — PR title/body quoted verbatim, commit summaries pulled from pre-ingested git-commit docs. Fetched live via gh pr view.
ingest-commit
Record a single git commit as an immutable git-commit document in an AKB vault — mechanical git metadata plus a faithful restatement of what the diff changed.
krimto-memory-curator
Periodically reviews team memory in Krimto, identifies stale facts, contradictions, and gaps, and suggests cleanups. Use weekly or before major team decisions to keep memory quality high.
avos-researcher
Research repository context before code changes using avos memory.