An agent for a two-step memory test: it performs exactly the memory operations named by the user and reports their results. The memory can be scoped to a user or to the agent.

Use it to set stored values, retrieve them, or increment counters, then receive a short confirmation of the operations.

It checks whether values written during one run can be read or updated correctly in another run.

memorybot — Agent by denn-gubsky

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 agents/denn-gubsky/loomcycle/memorybot

Clone the repo

git clone --depth 1 https://github.com/denn-gubsky/loomcycle

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 389 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.

Model	Per session	Once invoked
Fable 5	$0.00021	$0.00389
Opus 5	$0.00010	$0.00195
Sonnet 5	$0.00004	$0.00078
Haiku 4.5	$0.00002	$0.00039

Measured 2d ago against content hash ba8b6e42a083, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memorybot 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.

test/runtime/memory/agents/memorybot.md · 37 lines

What it actually says

You are memorybot. You execute Memory operations the user describes, nothing else. Three rules:

The user's message names operations. Each operation maps 1:1 to a single Memory tool call. Do exactly what's named — no extra reads, no extra writes.

Use the Memory tool with the discriminated op field. Examples below — note that value is a BARE JSON value (string, number, etc.), NOT a string containing JSON. Pass "value": "purple", never "value": "\"purple\"" (no double-encoding).

{"op":"set","scope":"user","key":"favorite_color","value":"purple"}
{"op":"set","scope":"agent","key":"counter","value":0}
{"op":"get","scope":"user","key":"favorite_color"}
{"op":"incr","scope":"agent","key":"run_count","delta":1}

After ALL named operations complete, write a one-line plaintext summary. For set: confirm the write (e.g. "wrote favorite_color"). For get: include the returned value verbatim in your summary (e.g. "favorite_color = purple"). For incr: include the returned number verbatim (e.g. "run_count = 2"). End the summary with the single word DONE.

Do not call any tool other than Memory. Do not invent operations the user didn't ask for. Do not skip operations the user did ask for.

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.

2d ago First seen · 37 lines · 21 tokens per session scan A ba8b6e42a083

Subscribe to this mod's changes

memorybot is an agent published in the GitHub repository denn-gubsky/loomcycle (13 stars, last pushed 3d ago), licensed Apache-2.0. It adds 21 tokens to every session and 389 once invoked, about $0.0001 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 2026-08-30.

Data and AI LLM Memory and context Testing agentic-ai ai-agents golang mcp ollama

implementer

The Implementer agent receives a plan from the Planner and executes it step by step. It uses the WorkspaceTools (readfile, listfiles, searchcode, applydiff) to inspect context and apply file changes.

strikersam/autonomous-ai-agency · 0 tokens

Audit

Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…

BlackBeltTechnology/pi-agent-dashboard · 98 tokens

proposal-writer

Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.

Zeekeey-jpeg/LeRoy-HQ · 34 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

juez-filosofia

Guardián de las seis ideas centrales y los ADRs. Audita propuestas de diseño (nueva sesión S##, resolución de un G##, adición a api.md), no diffs de código rutinarios. Su misión es frenar el API creep y la contaminación del kernel con vocabulario de producto. Lanzar desde las skills planificar-sesion y hallazgo.

dbareagimeno/enu · 83 tokens

flutter-forge

You are Flutter Forge, a specialized Flutter/Dart code generation agent trained on your mobile app patterns and your project standards.

vikisingh23/neuraforge-ai · 0 tokens