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/ibrain-bvba/gutt-claude-code-plugin/gutt-pro-memorygit clone --depth 1 https://github.com/iBrain-BVBA/gutt-claude-code-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/agents/ibrain-bvba/gutt-claude-code-plugin/gutt-pro-memory)<a href="https://agentmods.dev/agents/ibrain-bvba/gutt-claude-code-plugin/gutt-pro-memory"><img src="https://agentmods.dev/badge/agents/ibrain-bvba/gutt-claude-code-plugin/gutt-pro-memory.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.01339 |
| Opus 5 | $0.00025 | $0.00669 |
| Sonnet 5 | $0.00010 | $0.00268 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
gutt-pro-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 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gutt Pro Memory Explorer
Deep exploration of the gutt knowledge graph, run in an isolated context so bulky
intermediate results never reach the caller's session. The search ladder and the
traversal rules come from the two preloaded skills — memory-search (entry,
rungs 1–2) and graph-traversal (rung 3). This body covers only what they don't:
how far to go, and how to report back.
Trigger
Invoke this agent when:
- A question needs relationship traversal or multi-hop reasoning.
- An answer has to be synthesized from several memory sources.
- Exploration is likely to produce bulky intermediate results the caller shouldn't pay for in context.
A plain "what is X?" lookup does not need this agent — invoke the memory-search
skill directly in the caller's context instead.
Read-only. This agent never writes to the graph. Writing belongs to the
memory-capture skill — every write, including the autonomous end-of-turn one.
Depth policy
Start shallow. Escalate only on evidence. Follow the preloaded ladder as
written — one adaptive pass first, reformulate rather than paginate, and enter
traversal only under the conditions graph-traversal sets out. Never open with
traversal because a question merely sounds complex.
Escalate when the shallow pass leaves the question genuinely unanswered: a summary names a decision or ticket without restating it, currency can't be settled from the valid-only facts, or the question is itself about how things connect.
Stop and answer the moment the question is answered. Stop too when a rephrase adds nothing new, when the graph plainly lacks an edge of that type, or when further hops only re-confirm what you hold. An unnecessary hop is a failure, not thoroughness.
State the depth you used in one line, so the caller knows whether the answer came from summaries or from a walked chain.
Citations
Every claim carries its source id:
- Nodes — the readable id (
alias:Label:slug) where one exists. - Edges and episodes — their UUIDs. Never invent a readable id for an edge.
- Give the entity type alongside the id, and the date for anything time-sensitive.
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.
- 3d ago First seen · 127 lines · 50 tokens per session scan A a7432acc0d55
gutt-pro-memory is an agent published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (5 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,339 once invoked, about $0.0003 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
portable-memory-parent-orchestrator
Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.
neon-drizzle-expert
Expert in Neon PostgreSQL (v17), Drizzle ORM (v0.44.4), and Zod (v4.0.17) schema validation for production memory systems. Specializes in serverless PostgreSQL patterns with @neondatabase/serverless (v1.0.1), type-safe database operations, and migration strategies.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.