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 teamshared-ai/teamshared-plugin --skill teamshared-memorygit clone --depth 1 https://github.com/teamshared-ai/teamshared-pluginWrote 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/teamshared-ai/teamshared-plugin/teamshared-memory)<a href="https://agentmods.dev/skills/teamshared-ai/teamshared-plugin/teamshared-memory"><img src="https://agentmods.dev/badge/skills/teamshared-ai/teamshared-plugin/teamshared-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/teamshared-ai/teamshared-plugin/teamshared-memory"><img src="https://agentmods.dev/badge/skills/teamshared-ai/teamshared-plugin/teamshared-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 | $0.00054 | $0.02768 |
| Opus 5.5 | $0.00022 | $0.01107 |
| Sonnet 5.5 | $0.00011 | $0.00554 |
| Haiku 4.5 | $0.00005 | $0.00277 |
Grade A, and why
teamshared-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 23d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TeamShared memory (Claude Code)
The teamshared MCP server is your durable brain across sessions and repos.
Authenticated identity sets write attribution; do not pass agent unless you
intentionally override it or narrow a read filter. The MCP connection itself
uses Claude Code's own native OAuth flow — point the user at /mcp →
teamshared → Authenticate if it shows as needing authentication; that opens
a browser to the same email/OTP login as the web console and stores the token
for you. Never try to do this yourself. Do not call mcp_auth as the first
hop — it is a last-resort fallback after initialize when the host has no
token and /mcp isn't available.
The chat-capture hooks (below) are a separate subprocess with no access
to that OAuth token, so they authenticate independently with a tsk_ bearer
from TEAMSHARED_TOKEN (Authorization: Bearer tsk_…), minted with
teamshared token mint (org-scoped seat key) or at
https://teamshared.com/app/keys. They're optional — unset, they simply don't
capture anything, and the MCP connection and every-turn workflow are
unaffected. Never store or print the token. When the user asks to bind
or switch orgs, call org_list / org_context_get, then
org_bind(slug=..., scope=conversation|workspace). org_unbind clears
the overlay. teamshared org bind <slug> is an optional fallback; do
not add a second TeamShared server. Unbound /mcp keeps working. Point
humans at the console (/app) for sign-in, wiki, people, and keys.
This skill is protocol 1.31.0 — the same fetch/store loop as
rules/teamshared.mdc in the teamshared-plugin repo, adapted for Claude Code
(OAuth MCP connection, TEAMSHARED_TOKEN hooks, Claude write path). SessionStart
also injects the every-turn loop.
Unsure which tool? Call memory_tools_catalog(need="<intent>") — do not scan
every MCP descriptor, and do not call scope="memory", tier="core" as the only
discovery path (that hides files and projects).
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.
- 23d ago Changed · +1 lines af5e237d5ba1
- 1mo ago Changed · +12 lines 1833187b0bf4
- 1mo ago Changed · +9 lines 107f170a5b4c
- 1mo ago Changed · +130 lines · +15 tokens per session cca4ff13e67a
- 2mo ago First seen · 56 lines · 39 tokens per session scan A 51f41c70c582
teamshared-memory is a skill published in the GitHub repository teamshared-ai/teamshared-plugin (0 stars, last pushed 25d ago), licensed MIT. It adds 54 tokens to every session and 2,768 once invoked, about $0.0002 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 2026-09-08.
teamshared-memory compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| teamshared-memoryteamshared-ai/teamshared-plugin | Skill | 0 | 25d ago | MIT | A | 54 | Claude Code |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |