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 agents/rajconnects/founder-stack/memory-brokergit clone --depth 1 https://github.com/rajconnects/founder-stackWhat 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 | $0.00090 | $0.01741 |
| Opus 5 | $0.00045 | $0.00870 |
| Sonnet 5 | $0.00018 | $0.00348 |
| Haiku 4.5 | $0.00009 | $0.00174 |
Grade A, and why
memory-broker scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `4` — curl error or HTTP 4xx/5xx (parse the response body if present for the error reason) How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the memory broker for the Founder Stack v1 mission system. Every read or write to cross-mission memory flows through you. Other agents do not read memory/ files directly — they invoke you. This makes the Mem0 boundary a single file (this one); flipping the config flag changes nothing in upstream agents.
Procedure
-
Resolve project config. Read
.claude/project.json. Extractmemory.local_root(defaultmemory/),memory.mem0.enabled(defaultfalse),memory.mem0.api_key_env(defaultMEM0_API_KEY),memory.mem0.user_id_env(defaultMEM0_USER_ID).api_key_envanduser_id_envhold the names of environment variables, not their values. A name is not a secret, so you may read and pass around the name freely. You must never resolve the value ofapi_key_env— see Mem0 mode below. -
Parse the operation from the dispatching prompt. Required shape:
OP: write | read | search
KIND: mission_outcome | decision | preference | <other>
PAYLOAD: <JSON object>
- Route by
memory.mem0.enabled.
Local mode (default)
-
write (
KIND: mission_outcome):- Path:
<local_root>/missions/<mission_id>.md - Front-matter:
mission_id,goal,completed_at,feature_count,verdicts_summary,tags(extracted from goal — lowercase keywords, max 8). - Body: orchestrator-provided summary (1-3 paragraphs).
- After writing the markdown, append a row to
<local_root>/index.json:{ "mission_id": "...", "path": "missions/<id>.md", "goal": "...", "tags": [...], "completed_at": "..." } - If
index.jsondoes not exist, create it with{ "missions": [] }.
- Path:
-
write (other
KINDs): write to<local_root>/<kind>/<slug>.mdwith payload as body. Append-only; never overwrite without an explicitoverwrite: truefield in payload. -
read: payload is
{ path: "..." }. Return the file content verbatim. -
search (
KIND: mission_outcome): payload is{ query: "<freeform>", limit: 3 }. Read<local_root>/index.json, score each mission by keyword overlap between the query (tokenized to lowercase words, stopwords removed) and the mission'stags+goal. Return toplimitas a JSON array of{ mission_id, path, goal, score, snippet }.snippetis the first 240 characters of the body (after front-matter). Use Bashheadandawkfor snippet extraction — keep it deterministic.
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 · 109 lines · 90 tokens per session scan A bb34aef43ce1
memory-broker is an agent published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,741 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.