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 skills add Tangtaizong-BUAA/ArgonMemory --skill argon-memorygit clone --depth 1 https://github.com/Tangtaizong-BUAA/ArgonMemoryWrote 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/tangtaizong-buaa/argonmemory/argon-memory)<a href="https://agentmods.dev/skills/tangtaizong-buaa/argonmemory/argon-memory"><img src="https://agentmods.dev/badge/skills/tangtaizong-buaa/argonmemory/argon-memory/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/tangtaizong-buaa/argonmemory/argon-memory"><img src="https://agentmods.dev/badge/skills/tangtaizong-buaa/argonmemory/argon-memory.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 | $0.00031 | $0.00523 |
| Opus 5 | $0.00015 | $0.00262 |
| Sonnet 5 | $0.00006 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
argon-memory 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 8d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Argon Memory
Treat the configured Argon Memory MCP server as the project's durable memory. Do not create a competing truth store in chat summaries or local scratch notes.
Start every project task
- Call
kb_sync_skillonce and apply only a validated incremental Skill delta when required. - Call
kb_briefwith the stableproject_id. Read the complete main file and live section navigation. - Select the relevant section and call
kb_graph_contextwith the user's original query. - For names, dates, numbers, versions, quotations, decisions, images, tables, or evidence, proactively call
kb_search, then inspect the matching record or Artifact withkb_graph_contextorkb_read.
The main file is an orientation map. Maintained sections provide domain synthesis. Artifacts remain the evidence layer. Never use a summary as a substitute for a verifiable source.
Durable work loop
- Before material work, call
kb_start_work. - Publish long-lived outputs with
kb_publish_resource; use chunked upload tools for large resources. - Distill stable facts, decisions, constraints, preferences, procedures, lessons, and open questions with
kb_capture_context. Never upload a raw conversation transcript. - Close every work item with
kb_finish_work, including partial or failed work, evidence, outputs, and unresolved issues.
Memory candidates may be accepted, quarantined, disputed, or rejected. Report that status honestly. Never present quarantined or disputed memory as confirmed fact.
Conflicts and authority
Disclose relevant open or resolution_pending conflicts. Do not silently choose a winning claim based on recency, source order, or model judgment. Only a principal with the resolver capability may persist an owner's explicit resolution through kb_submit_user_resolution; other agents may use the answer for the current response but must not write it back through another tool.
Safety
- Never place credentials, private keys, or tokens in MCP arguments or records.
- Use
kb://resource identifiers, never server filesystem paths. - Original Artifacts and audit events are append-only. Archive, supersede, or detach instead of deleting history.
- Respect the server's profile and confidentiality boundaries. Do not attempt to obtain tools hidden from the current principal.
What ships with it
2 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.
- 8d ago First seen · 40 lines · 31 tokens per session scan A fb6864afbb52
argon-memory is a skill published in the GitHub repository Tangtaizong-BUAA/ArgonMemory (1 stars, last pushed 12d ago), licensed Apache-2.0. It adds 31 tokens to every session and 523 once invoked, about $0.0002 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
openlore
Query and publish to an OpenLore knowledge base over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.
openlore-housekeeping
Audit and maintain a shared OpenLore knowledge base. Use on a schedule or on request to find stale docs, broken links, unreviewed inbox items, and missing skill coverage, then publish an audit report.
kb
Set up, evolve, or operate a hraness/kb local-first Markdown knowledge base for coding-agent memory. Use when a user asks to design KB conventions or a recurring KB ritual; search or query a KB or Obsidian vault; load or recover repository context, plans, decisions, concepts, backlinks, semantic search, or Git…
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
unforgit-memory
Use Unforgit MCP tools as durable repository memory for decisions, conventions, gotchas, and playbooks.
mk:wiki
Capture, gate, query, and render long-term project knowledge through the gated mewkit wiki subsystem. Use to create a wiki, propose/approve candidates (scanner-gated), hand off a skill's terminal artifact as a scanned candidate, recall context, search the FTS index, or list pages. Agents may only PROPOSE candidates…