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/jscott3201/aionforge-memory/agent-messagingnpx skills add jscott3201/aionforge-memory --skill agent-messaginggit clone --depth 1 https://github.com/jscott3201/aionforge-memoryWrote 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/jscott3201/aionforge-memory/agent-messaging)<a href="https://agentmods.dev/skills/jscott3201/aionforge-memory/agent-messaging"><img src="https://agentmods.dev/badge/skills/jscott3201/aionforge-memory/agent-messaging.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 | $0.00079 | $0.01640 |
| Opus 5 | $0.00039 | $0.00820 |
| Sonnet 5 | $0.00016 | $0.00328 |
| Haiku 4.5 | $0.00008 | $0.00164 |
Grade A, and why
agent-messaging 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Messaging
Requires an enabled Aionforge Memory MCP server.
Use this skill for directed agent-to-agent delivery: a brief handed to another
agent, a status page, a review verdict, an acknowledgement. A Message is a
first-class node that is deliberately separate from both memory episodes and work
items — it is never returned by search, and it never enters consolidation, decay,
or the forget sweep. Reach for it when a specific recipient needs to receive
something, not when a fact needs to be remembered (capture) or a task needs to be
tracked (work_create).
Message vs memory vs work — route deliberately
- A durable fact future agents may recall →
capture(a decaying episode; seememory-capture). - A task, blocker, or follow-up to track to completion →
work_create/work_advance(a persistent work item; seework-tracking). - Something a named agent or team must receive now →
message_send(a durable, addressed message). It is delivered to that recipient's inbox, not into shared recall.
A brief posted to a teammate is a message. The durable decision behind that brief
is still a capture; the work it creates is still a work_create. Messaging does
not replace either — it carries the delivery.
Addressing and identity
- Resolve identity once: prefer
AIONFORGE_AGENT_ID; otherwise use the stable agent UUID from the user or project instructions. Reads and sends takeviewer: agent:<uuid>(or an explicitprincipal). - A recipient is either
agent:<uuid>(a direct message into that agent's private inbox) orteam:<name>(a broadcast into a team namespace you are authorized to write). Direct delivery is the one intentional cross-agent write in the system: you may only place aMessagein the recipient's namespace, never a memory or work item. - On every read (
message_poll,message_wait, a room read) assert the teams you belong to (e.g.teams: ["aionforge-memory-team"]). Read authorization is per-call: a team inbox is out of scope unless you assert that team in the same call. Never assert a team you are not a member of.
What ships with it
1 file 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.
- 5d ago First seen · 111 lines · 79 tokens per session scan A 96ede953d690
agent-messaging is a skill published in the GitHub repository jscott3201/aionforge-memory (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,640 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
brain-write
How to write to the INITE Brain knowledge graph from an agent loop — recordfact (with the conversationId / evidence[] grounding inputs), ingestdocument, linkentities, retractfact, recordfeedback, and the detectcontradiction preflight. Covers confidence picking, claim grounding, retract vs forget semantics, identityof…
brain-bitemporal
How to query the INITE Brain knowledge graph across time — the asOf parameter, validFrom/validUntil semantics, reading retracted facts, and the memorydiff "what changed between two cursors" surface. Use when the user's question has a temporal dimension ("on X date", "before Y", "what's new since last conversation").
brain-conflict
How to detect and resolve conflicting beliefs in the INITE Brain knowledge graph — the COMPETING fact status, getcompetingfacts, detectcontradiction preflight, and the human-in-the-loop adjudication workflow. Use when the timeline shows two facts disagreeing on the same predicate, or when an agent needs to decide what…
brain-recall
Recall everything brain knows about one specific entity — current profile, full bitemporal timeline, graph neighbours, and unresolved disagreements. Use when the user names a person/company/thing and asks "tell me about them", "what's their history", or "what do we still disagree about?". For a single-shot LLM…
memory-review
Memory hygiene audit -- finds stale facts, contradictions, low-confidence entries, and consolidation candidates in Pensyve memory. Use periodically to maintain memory quality.
context-loader
Session-start context loading -- loads historical decisions, issues, and patterns from Pensyve to provide cross-session continuity. Use at session start or when switching context.