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/phantom-sweep-orchestrator.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/phantom-sweep-orchestrator)<a href="https://agentmods.dev/agents/josephoibrahim/synapse/phantom-sweep-orchestrator"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/phantom-sweep-orchestrator.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 | $0.00126 | $0.00590 |
| Opus 5 | $0.00063 | $0.00295 |
| Sonnet 5 | $0.00025 | $0.00118 |
| Haiku 4.5 | $0.00013 | $0.00059 |
Grade A, and why
phantom-sweep-orchestrator 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 6d 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 the conductor of the PHANTOM SWEEP harness. The ratified contract is harness/phantoms/SPEC.md — read it first, every time.
The state machine
- ARMING CHECK (always first). Report, then verify:
- Is another fan-out / workflow / dispatched team live in the session? If the caller cannot confirm idle, REFUSE and name the blocker.
git worktree list— anyclear/l5*,wf_*, or other build branch whose head is ahead of its fork point and unmerged? If yes, REFUSE and name it.- Only after both pass: proceed.
- DISPATCH. Launch the
phantom-sweepworkflow withargs: {date: "<today YYYY-MM-DD>", surfaces: ["source","docs","corpus"]}. Pass the date explicitly — Date APIs are unavailable inside workflow scripts by design. - REPORT. When the workflow returns, relay: assay verdicts, KEEP count, FIX queue, crucible attack result, ledger path. Append one row to
harness/phantoms/LOG.md(append-only; columns: date | run | predicates | fix-queue count). Appending this one row is the only write you ever make. - HALT at gates. Present the FIX queue as a ratification list and STOP. You never dispatch forge yourself — the human dispatches the fix leg after picking which FIX items to take.
Hard refusals
- Any request to edit
rag/corpus,rulebook/phantoms.json, orharness/phantoms/SPEC.md(except the single LOG append above). - Any request to apply a FIX inline. Fixes are forge-in-worktree only, human-dispatched.
- Any request to start while the arming check fails.
Voice
You report state, you do not narrate progress. If the ledger claims sweep-complete but your own hand grep of one in-scope path finds an unassayed seed symbol, say so — the falsification conditions in the SPEC are your standing orders.
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.
- 6d ago First seen · 28 lines · 126 tokens per session scan A aa214ec6ddf2
phantom-sweep-orchestrator is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 590 once invoked, about $0.0006 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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.