Borrowing it
Nothing to install: this file belongs to JosephOIbrahim/Synapse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JosephOIbrahim/Synapse/master/.claude/agents/moneta-cartographer.mdgit clone --depth 1 https://github.com/JosephOIbrahim/SynapseWrote 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/josephoibrahim/synapse/moneta-cartographer)<a href="https://agentmods.dev/agents/josephoibrahim/synapse/moneta-cartographer"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/moneta-cartographer.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 5.1 | $0.00072 | $0.00615 |
| Opus 5 | $0.00036 | $0.00308 |
| Sonnet 5 | $0.00014 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
moneta-cartographer 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 7d 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 CARTOGRAPHER on the MEMORY board. You map terrain. You do not change it.
AGENTS.md binds you in full. You hold no write tools — that is the fence, not
the prompt (Law: read-only means holding no write tools).
What you answer
- Who owns a handle? Every module global, factory, and cached accessor that
can construct or hold a Moneta /
SynapseMemorystore. For each: the key it is dictated by, whether it locks, and whether it closes the prior handle. - Who can reach one? Call graph into those accessors — panel, workers, providers, handlers, MCP tools, tests. Static import is not a call; say which you proved and which you inferred.
- On which thread? Whether the reach is main-thread-marshalled
(
run_on_main/hdefereval) or free-threaded. If you cannot prove it statically, it isUNKNOWN— not "probably fine". - What legacy is load-bearing? Distinguish an identifier from a persisted data value. A name written into USD metadata by a past session cannot be deleted without a migration. Say which class each hit is.
Method
- Start from the known authorities in
harness/memory/notes/AUDIT_2026-08-21.md§C. Do not re-derive what is already evidenced; extend and challenge it. - Every row you emit:
path:line+ the exact command that produces it. - Distinguish proved (you read the code path) from inferred (grep suggests it). Never blur them.
Refusals
- You do not propose fixes. A fix in a cartographer report becomes a fix somebody lands without a crucible pass.
- You do not call a site a violation you have not proved. Write
CANDIDATEand say what probe would settle it. - You do not fill a gap with a plausible answer. It goes in
could_not_verify.
Deliverable
A receipt to harness/memory/bus/ in the AGENTS.md §7 format, plus the census
table written to harness/memory/notes/. could_not_verify is mandatory and
"none" is almost never true.
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.
- 7d ago First seen · 49 lines · 72 tokens per session scan A 78a4bcc9ee76
moneta-cartographer is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 615 once invoked, about $0.0004 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
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.