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/apiliumcode/mayros/akashinpx skills add ApiliumCode/mayros --skill akashigit clone --depth 1 https://github.com/ApiliumCode/mayrosWhat 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 | $0.00069 | $0.01000 |
| Opus 5 | $0.00034 | $0.00500 |
| Sonnet 5 | $0.00014 | $0.00200 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
akashi 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 2d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Akashi: the user's second brain, connected
Akashi is a local-first, encrypted knowledge vault with a semantic engine
(AIngle, the same engine inside Mayros). It runs on the user's machine and
serves an MCP endpoint at http://127.0.0.1:19191/mcp with a bearer token.
Retrieval is grounded: every passage carries source:lines citations and a
cryptographically signed provenance anchor. Measured on the standard demo
vault: about 94% fewer input tokens than pasting notes into context.
1. Connect (once)
If aingle_ground and the other aingle_* tools are already available, you
are connected. Skip to section 2.
Otherwise, add Akashi as an MCP server in the mcp-client extension config:
{
"servers": [
{
"id": "akashi",
"name": "Akashi vault",
"transport": {
"type": "http",
"url": "http://127.0.0.1:19191/mcp",
"authToken": "<TOKEN>"
},
"autoConnect": true
}
]
}
The user creates <TOKEN> in the Akashi app: Settings, "AI & connections",
"Access tokens", named mayros. One token per runtime: revoking one never
disconnects the rest. Akashi is a free download for macOS, Windows, and Linux
at https://apilium.com/en/products/akashi.
If the connection is refused, Akashi is not running: ask the user to open it. On HTTP 401 the token was revoked: mint a new one.
2. Query-first protocol (the core rule)
BEFORE answering anything that may touch the user's knowledge (projects, past decisions, conventions, people, notes, plans), query the vault:
aingle_ground {question, k}: the primary tool. Returns cited passages (source,lines,text, signed provenance anchor), agroundednessverdict, and aninstructionyou MUST follow.aingle_vault_map: orientation. Hubs, semantic clusters, indices.aingle_note_context {note}: the verified neighborhood of one note.aingle_sources: what is indexed, with content hashes.- To trace how two notes or topics connect: call
aingle_note_contexton each and intersect their neighborhoods, or walkaingle_backlinksfrom one side; report the connecting chain with citations for every hop.
What ships with it
8 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.
- 2d ago First seen · 94 lines · 69 tokens per session scan A 02a0bc592cad
akashi is a skill published in the GitHub repository ApiliumCode/mayros (12 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,000 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 2026-08-30.
Other skills, from other repositories
campaign
Start, drive, monitor, and stop an Autonomous Improvement Campaign — a durable, repeatable wrapper around the dev-improve loop.
dev-loop
Pull the next task from a platform Ralph Loop queue (via the devloop MCP bridge) and drive it to a verified, committed, reported outcome. One task per invocation — this is a Ralph-pattern loop body designed to be driven repeatedly by /loop /dev-loop.
improve
Discover, offer, and triage code-quality improvements for the dev-improve loop.
gen-tests
Generate RSpec request specs for untested controllers and service specs for untested services.
verify
Run targeted verification based on what changed since last commit.
audit
Run comprehensive codebase quality and pattern compliance audit.