agent-memory-protocol

A protocol for giving an agent an identity when it reads or writes the gutt knowledge graph, a stored network of organizational information and relationships.

In plain words
What is it for?
Use it when a named or role-based agent needs to search its own memories, use group knowledge, or save lessons with the required identity tags.
Why use it?
It keeps memories associated with the correct agent and scope, while defining how the agent should recall and record information.

Skill for Claude CodeCodex

Part of the gutt-pro plugin — 11 skills, 10 commands, 2 agents, 5 hooks shipped together

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 skills/ibrain-bvba/gutt-claude-code-plugin/agent-memory-protocol
Any agent
npx skills add iBrain-BVBA/gutt-claude-code-plugin --skill agent-memory-protocol
Clone the repo
git clone --depth 1 https://github.com/iBrain-BVBA/gutt-claude-code-plugin

Made for: Claude Code, Codex.

Or install gutt-pro, the plugin that ships this one along with the rest of its 11 skills, 10 commands, 2 agents, 5 hooks.

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,821 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00108 $0.01821
Opus 5 $0.00054 $0.00911
Sonnet 5 $0.00022 $0.00364
Haiku 4.5 $0.00011 $0.00182

Measured 3d ago against content hash d01da2f34455, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-memory-protocol 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 3d 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.

gutt-core/skills/agent-memory-protocol/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Memory Protocol

How an agent works the gutt knowledge graph as itself: register a memory identity, recall your own scope before the group's, and tag every write you make so the next run of you can find it. This layers agent identity on top of memory-search (how to read) and memory-capture (how to write). The identity convention — naming, registration, tagging, recall order, guard rails — lives in one normative place: references/agent-identity.md. This file is the operative digest; on any conflict, the reference wins.

Use this when you act as a named agent (a subagent, a role agent). Writing from the main session with no agent identity is just memory-capture — no registration, no tagging.

Finding the scope bound to this directory (do this before step 1)

Your registered name carries a --<scope> suffix, and the first place to look for its value is the binding a person set with /gutt-pro:agent-scope. You cannot run that command to ask — it only takes effect when a human types it — so read the stored value directly:

  • <DATA_DIR>${CLAUDE_PLUGIN_DATA}, interpolated into this sentence for you. Do not pass $CLAUDE_PLUGIN_DATA through to a shell and do not export it: only hooks are given it, so it expands to nothing in a command you run.
  • Read <DATA_DIR>/config.json and look under projects. The key is the name Claude Code gives this project's transcript directory, which you can derive from your working directory: resolve its symlinks, then replace every path separator, drive-letter colon, . and _ with a single - — each character becomes its own dash, so two adjacent ones yield -- (this is not the run-collapsing rule scope values are normalised with). So /Users/me/my_app is -Users-me-my-app, /Users/me/.config/app is -Users-me--config-app, and on Windows C:\dev\my.app is C--dev-my-app. Take projects.<that key>.agentScope.value.
    • Resolve the symlinks first (pwd -P): on macOS /tmp and /var are links into /private, and the unresolved spelling gives a key that never matches.
    • Match the key exactly. If nothing matches, treat it as unbound and fall through — never pick the closest-looking entry, because a wrong match binds this directory to another one's identity, permanently.

Read the full file on GitHub · 118 lines

Files

What ships with it

1 file 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.

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.

  1. 3d ago First seen · 118 lines · 108 tokens per session scan A d01da2f34455

Subscribe to this mod's changes

agent-memory-protocol is a skill published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (4 stars, last pushed 12d ago), licensed MIT. It adds 108 tokens to every session and 1,821 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens