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 instructions/zzhang82/agent-memory-bridge/agents-mdgit clone --depth 1 https://github.com/zzhang82/Agent-Memory-BridgeWhat 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 | $0.01089 | $0.01089 |
| Opus 5 | $0.00544 | $0.00544 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
Agent-Memory-Bridge AGENTS.md 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 2d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Memory Bridge Contributor Instructions
These instructions are self-contained. Contributors only need this repository, Python, and the documented toolchain; no external profile, memory service, or machine-specific setup is required.
Setup And Checks
- Use Python 3.11 or newer.
- Install dev dependencies from the repo root:
python -m venv .venv
python -m pip install -e ".[dev]"
- Run the main test suite:
python -m pytest
- Run lint and format checks:
ruff check src tests scripts
ruff format --check src tests scripts
- Run the Linux CI typecheck target. On Windows, add
--platform linuxso mypy checks the same platform contract as CI instead of rejecting POSIX-only process APIs during local analysis:
mypy src/agent_mem_bridge/schema.py src/agent_mem_bridge/storage.py src/agent_mem_bridge/provenance.py src/agent_mem_bridge/repository.py src/agent_mem_bridge/signals.py src/agent_mem_bridge/query.py src/agent_mem_bridge/state_io.py src/agent_mem_bridge/command_provider.py src/agent_mem_bridge/database_maintenance.py src/agent_mem_bridge/release_contract.py src/agent_mem_bridge/run_ledger.py src/agent_mem_bridge/run_outcome_authority.py src/agent_mem_bridge/run_projection.py src/agent_mem_bridge/run_consolidation.py src/agent_mem_bridge/server.py src/agent_mem_bridge/mcp_boundary.py src/agent_mem_bridge/stdio_probe.py
- For release-facing or public-surface changes, also run:
python ./scripts/run_benchmark.py
python ./scripts/run_deterministic_proof.py
python ./scripts/check_release_contract.py
python ./scripts/check_public_surface.py
python ./scripts/check_onboarding_contract.py
Architecture Boundaries
- Runtime code lives in
src/agent_mem_bridge; tests live intests; proof and regression fixtures live inbenchmark; operational entry points live inscripts. server.pydefines the public MCP surface. Keep the tool contract small and explicit:store,recall,browse,stats,forget,feedback,promote,annotate,revise,export,begin_run,record_run_event,get_run,complete_run,claim_signal,extend_signal_lease, andack_signal.storage.py,repository.py, andschema.pyown durable record behavior.signals.pyowns Signal lifecycle rules.query.pyand index modules own retrieval and derived indexes.- CLI reports, review queues, Task Briefs, activation receipts, benchmarks, and context assembly are not separate public MCP tools unless a reviewed contract change explicitly adds them.
- Worker execution, hosted identity, OAuth, per-namespace ACLs, sandboxing, remote multi-user coordination, and distributed locking are outside the core bridge boundary unless the implementation and public docs both change.
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.
- 2d ago First seen · 108 lines · 1,089 tokens per session scan A cacaab48ea5d
Agent-Memory-Bridge AGENTS.md is an instructions file published in the GitHub repository zzhang82/Agent-Memory-Bridge (6 stars, last pushed 2d ago), licensed MIT. It adds 1,089 tokens to every session, about $0.0054 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 instructions, from other repositories
mnemic CLAUDE.md
Claude Code instructions for dongtang3/mnemic: This project includes a project-level .mcp.json for the Mnemic memory MCP server.
mcp-light-memory AGENTS.md
AGENTS.md instructions for PeterPirog/mcp-light-memory, covering agent operating contract and persistent agent memory: mcp light memory (internalrag).
mnemic AGENTS.md
AGENTS.md instructions for dongtang3/mnemic: Mnemic is a graph-backed long-term memory substrate for coding agents and LLM applications.
personal-model AGENTS.md
Instructions for Intuition-Lab/personal-model, covering agents.md, runtime boundary, commands, pipeline and documentation map.
plur CLAUDE.md
Instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
engraphis AGENTS.md
Instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, 0. read this first — two architectures live in one package, 1. commands, ── unified dashboard + memory inspector ── and 2. the v2 recall pipeline (where the real work is).