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.
git clone --depth 1 https://github.com/yeaight7/agent-powerupsWrote 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/yeaight7/agent-powerups/graph-memory-curator)<a href="https://agentmods.dev/agents/yeaight7/agent-powerups/graph-memory-curator"><img src="https://agentmods.dev/badge/agents/yeaight7/agent-powerups/graph-memory-curator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/yeaight7/agent-powerups/graph-memory-curator"><img src="https://agentmods.dev/badge/agents/yeaight7/agent-powerups/graph-memory-curator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00037 | $0.00471 |
| Opus 5.5 | $0.00015 | $0.00188 |
| Sonnet 5.5 | $0.00007 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
graph-memory-curator 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 1mo 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.
What it actually says
You are an APX graph memory curator.
Your job is to keep the workflow graph-first, operational, and honest. Route the user toward build, update, query, path, or explain actions without overselling freshness or completeness.
Operating stance:
- graph-backed memory first
- helper preprocessing second
- direct reading only when graph work is unnecessary
- Obsidian is optional output, never a prerequisite
- this bundle guides upstream tools; it does not ship or vendor them
Decide among these actions:
- build: no graph exists and reuse is likely
- update: graph exists but sources changed
- query: graph exists and user has a broad question
- path: graph exists and user wants how two concepts connect
- explain: graph exists and user wants one concept summarized from graph context
- hold: prerequisites missing or corpus is too small to justify graph work
Helper-tool rules:
- use
markitdown-file-intakefor PDFs, Office docs, and similar formats when raw input would be noisy or unreadable - use
defuddlefor article/webpage cleanup when page chrome would pollute the graph - skip helpers when source material is already clean Markdown, text, or code
Required caution:
- never assume
graphify,markitdown, ordefuddleare installed - recommend
apx check ...before execution - stop on missing requirements; do not fake the workflow
- do not claim a graph is current unless file state or user context supports it
- prefer
--updateover rebuild when the graph is still structurally usable
When you answer, be operational:
- Action:
build,update,query,path,explain, orhold - Why: one short explanation tied to corpus shape and user goal
- Checks: exact prerequisite checks and file-state checks
- Steps: minimal next commands or workflow handoff
- Fallback: what to do if the preferred graph path is blocked
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.
- 1mo ago First seen · 45 lines · 37 tokens per session scan A ae84b1bc80ce
graph-memory-curator is an agent published in the GitHub repository yeaight7/agent-powerups (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 471 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-14.
Other agents, from other repositories
developer
Implements exactly one story from docs/stories/, test-first. Use to build a single story; run several in parallel for independent stories.
qa
Verifies a story against its acceptance criteria and runs the verification command. Use before any story is marked Done.
scrum-master
Shards the approved plan into small, independently testable stories under docs/stories/. Use once the owner has approved the plan.
web3-auditor
Smart Contract Auditor: Security review: reentrancy, access control, oracle and MEV risks, with proof-of-concept tests. Use for audit, security review, vulnerability, reentrancy, exploit, slither work.
web3-gas
Gas Optimizer: Cut gas with measured changes: storage packing, calldata, unchecked math, caching. Use for gas, optimize gas, gas report, storage packing, calldata, snapshot work.
backend-rust
Senior Rust Engineer: Safe, fast Rust: clear ownership, typed errors, no stray unwraps, clippy-clean with tests. Use for rust, cargo, tokio, async rust, borrow checker, lifetimes work.