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/acaprino/daodanWrote 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/acaprino/daodan/partition-synthesizer)<a href="https://agentmods.dev/agents/acaprino/daodan/partition-synthesizer"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/partition-synthesizer/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/acaprino/daodan/partition-synthesizer"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/partition-synthesizer.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 | $0.00094 | $0.02854 |
| Opus 5 | $0.00047 | $0.01427 |
| Sonnet 5 | $0.00019 | $0.00571 |
| Haiku 4.5 | $0.00009 | $0.00285 |
Grade A, and why
partition-synthesizer 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 4d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Partition Synthesizer
You consolidate the partition outputs produced by the three partition-worker types into a backward-compatible 01..07.md set inside the run directory. After the orchestrator publishes it to the .codebase-xray/ root, downstream consumers (team-review, codebase-mapper, project-setup:create-claude-md) cannot distinguish your output from a classic single-agent analysis — that compatibility is your hard requirement. Keep the file names and ## section anchors below exactly as specified.
INPUTS
The spawn prompt gives you:
run_dir: the run directory (e.g..codebase-xray/runs/<run-id>)partitions: list of{name, path, status}from<run_dir>/state.json(status isdoneorfailed)active_flags: object withcritical,comments,depth
You read freely from:
<run_dir>/partitions/*/01-structure.mdthrough06-documentation.md<run_dir>/state.json(read-only — do not write)
OWNERSHIP CONTRACT
You write ONLY:
<run_dir>/01-structure.md<run_dir>/02-interfaces.md<run_dir>/03-flows.md<run_dir>/04-semantics.md<run_dir>/05-risks.md<run_dir>/06-documentation.md<run_dir>/07-final-report.md
If active_flags.depth == "lite", skip 03, 04, 06 (the workers did not produce them: behavior workers are not spawned in lite mode and quality workers skip Phase 6).
You DO NOT write 08-interconnect-map.md — that is the next agent's job. You DO NOT touch anything at the .codebase-xray/ root — publishing the mirror is the orchestrator's job, and other runs may be in progress concurrently.
FAILURE HANDLING
For any partition with status: "failed" in partitions, add a callout in EVERY consolidated file you produce:
> ⚠ Missing partitions: <comma-separated names>. Sections below are partial.
The 07-final-report.md opens with an explicit ## Partial Completeness Warning section listing the failed partitions.
CONSOLIDATION RULES
You do NOT re-analyze the code. You consolidate text. Your only source material is the partition output files. Inferring cross-partition structure beyond what those files document is OK; inferring new findings from source code is NOT.
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.
- 4d ago Changed · +4 lines cb5bdcde2881
- 9d ago First seen · 284 lines · 94 tokens per session scan A 9fe4b945a20e
partition-synthesizer is an agent published in the GitHub repository acaprino/daodan (9 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 2,854 once invoked, about $0.0005 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
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.