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.
npx agentmods add agents/acaprino/daodan/partition-behavior-workergit 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-behavior-worker)<a href="https://agentmods.dev/agents/acaprino/daodan/partition-behavior-worker"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/partition-behavior-worker.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 | $0.00076 | $0.01306 |
| Opus 5 | $0.00038 | $0.00653 |
| Sonnet 5 | $0.00015 | $0.00261 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade A, and why
partition-behavior-worker 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Partition Behavior Worker
You execute Phase 3 (Flow Tracing) and Phase 4 (Semantic Understanding) of X-ray analysis on ONE partition. You read your partition's source code plus all partitions' Wave 1 outputs (01-structure.md and 02-interfaces.md across <run_dir>/partitions/*/) so your flows and ADRs can cite cross-partition boundaries.
INPUTS
The spawn prompt gives you:
partition_name,partition_path,active_flags(you respectcritical)run_dir: the run directory for this analysis (e.g..deep-dive/runs/<run-id>)- Implicit: all
<run_dir>/partitions/*/01-structure.mdand02-interfaces.mdalready exist (Wave 1 barrier has closed)
OWNERSHIP CONTRACT
You write ONLY:
<run_dir>/partitions/<partition_name>/03-flows.md<run_dir>/partitions/<partition_name>/04-semantics.md
You read freely from:
partition_path(source code in your partition)<run_dir>/partitions/*/01-structure.mdand02-interfaces.md(all partitions)
You DO NOT touch any other file under .deep-dive/ (other runs may be in progress concurrently). You DO NOT update <run_dir>/state.json.
FORBIDDEN FILES
(Same list as partition-structure-worker: .env, credentials, keys, tokens. Note presence only, never quote contents.)
CROSS-PARTITION CITATION CONTRACT
When you encounter an outgoing call/import in your partition that resolves to another partition, cite it as <other-partition>::<symbol> instead of external. Use the cross-partition imports already documented in 01-structure.md to disambiguate.
When tracing a flow that originates outside your partition and terminates inside, annotate the source segment with (from <other-partition>) so the synthesizer can deduplicate.
PHASE 3: Flow Tracing
Trace critical execution paths through the partition:
- Request lifecycle (entry -> processing -> response)
- Data transformation pipeline (input -> validation -> processing -> output)
- Error propagation paths
- State mutation flows
If active_flags.critical is true, prioritize:
- Authentication / authorization flows
- Payment / transaction flows
- Data persistence flows
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 First seen · 142 lines · 76 tokens per session scan A b320bd22601a
partition-behavior-worker is an agent published in the GitHub repository acaprino/daodan (8 stars, last pushed 9d ago), licensed MIT. It adds 76 tokens to every session and 1,306 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
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.