What is shared-agents-knowledge?

A shared team-knowledge system that synchronizes approved lessons and agent skills between sessions. It also defines where pending lessons belong.

Use it to sync team knowledge, check its status, search approved lessons, and manage approved or pending learning files in the canonical location.

It keeps shared guidance available to agents and reduces conflicting copies or forgotten updates.

shared-agents-knowledge — Cursor rule by netgrade-digital

Install

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.

agentmods

npx agentmods add rules/netgrade-digital/shared-agents/shared-agents-knowledge

Clone the repo

git clone --depth 1 https://github.com/netgrade-digital/shared-agents

Per session 704 This file is loaded in full into every session.

When invoked 704 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00704	$0.00704
Opus 5	$0.00352	$0.00352
Sonnet 5	$0.00141	$0.00141
Haiku 4.5	$0.00070	$0.00070

Measured yesterday against content hash 3d8c473882de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shared-agents-knowledge 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 yesterday.

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.

rules/shared-agents-knowledge.mdc · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Knowledge (shared-agents)

Repo: $SHARED_AGENTS_HOME (default ~/.shared-agents). Paths: $SHARED_AGENTS_HOME/docs/canonical-paths.md

Shell commands (canonical — do not duplicate here): run sa help
Without bashrc alias: "${SHARED_AGENTS_HOME:-$HOME/.shared-agents}/scripts/sa" help
Also: shared-agents · sharedagents · bare sa = same as sa help
Full guide for users/agents: skill sa-cli

Automatic sync (mandatory — never ask the user)

At the start of every agent session, before any other work:

Run: "${SHARED_AGENTS_HOME:-$HOME/.shared-agents}/scripts/sa" sync
(same as scripts/sync.sh pull — prefer sa sync)
Do not ask permission. Do not mention sync unless it failed and blocks the task.
If pull fails (offline): continue with local copy; retry sync before reading learnings.
After sa sync (non-quiet) or on request: run sa status --brief — if action needed, tell the user briefly (pending reviews, skill links, adapters).

Cursor also runs sessionStart hook — still run sync once at session start if unsure hook ran.

Before tasks

After sync, search $SHARED_AGENTS_HOME/team/learnings/approved/ and $SHARED_AGENTS_HOME/team/learnings/index.yaml for matching project/domain. Use skill shared-agents-knowledge.

After tasks (mandatory for non-trivial work)

After a non-trivial task (feature, bugfix, refactor, multi-file change, non-obvious fix):

Always ask the user: „Soll ich ein Team-Learning in shared-agents anlegen?"
Wait for explicit yes/no.
If yes: skill capture-learning — paths, format, publish workflow (see skill). Shell: skill sa-cli or sa help.
If no: stop — do not write anything.
Tell user: pending/ is draft only; promotion to approved/ is human sa review (skill sa-cli or sa help).

Skip the question only for trivial work (typos, formatting, pure Q&A, no reusable insight).

No secrets. Agent never writes approved/.

Read the full file on GitHub · 57 lines

Changes

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.

yesterday First seen · 57 lines · 704 tokens per session scan A 3d8c473882de

Subscribe to this mod's changes

shared-agents-knowledge is a cursor rule published in the GitHub repository netgrade-digital/shared-agents (4 stars, last pushed 2mo ago), licensed MIT. It adds 704 tokens to every session, about $0.0035 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.

Git and workflow Learning and teaching Memory and context ai-agents claude-code cli codex cursor developer-tools

shared-agents-knowledge

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Team Knowledge (shared-agents)

Automatic sync (mandatory — never ask the user)

Before tasks

After tasks (mandatory for non-trivial work)

What this file has done since we first saw it

Other cursor rules, from other repositories

egc-context

cursorrules

self-correction

memory-protocol

haive-memories

debugging