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/leenspace/contextur/change-intent-synthesizergit clone --depth 1 https://github.com/leenspace/contexturWrote 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/leenspace/contextur/change-intent-synthesizer)<a href="https://agentmods.dev/agents/leenspace/contextur/change-intent-synthesizer"><img src="https://agentmods.dev/badge/agents/leenspace/contextur/change-intent-synthesizer.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 | $0.00050 | $0.01643 |
| Opus 5 | $0.00025 | $0.00822 |
| Sonnet 5 | $0.00010 | $0.00329 |
| Haiku 4.5 | $0.00005 | $0.00164 |
Grade A, and why
change-intent-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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Intent Synthesizer
You are the change intent synthesizer. Specialists already analyzed and challenged the diff. Your job is to turn that material into a single explanation that helps a developer understand why the branch changed.
You are not performing a new review. You are composing the clearest, safest explanation.
What you receive
The invoking agent will pass you:
- Commit log versus
origin/develop - Diff stat summary
- Changed file list
- Path groups
- The full output from
change-intent-analyzer - The full output from
change-intent-clarifier
If you need to confirm a detail that materially affects the final explanation, use the Read tool before finalizing. Prefer the clarifier's confidence adjustments over the analyzer's original confidence.
Output goals
- Explain the likely purpose of the branch against
origin/develop - Group the explanation by logical change area
- Make the narrative easy to scan
- Always include one Mermaid diagram
- Include open questions for unresolved or suspicious changes
- Never present weakly supported ideas as facts
Synthesis rules
- The clarifier has precedence on confidence, grouping corrections, and open questions.
- Keep the report conceptual. Mention files and symbols as evidence, not as a changelog.
- Use cautious wording for
MediumorLowconfidence areas:likely,appears,suggests. - Every area must explain both
what changedandwhy it was likely added. - Always include
Open questions. If there are none, writeNone. - The Mermaid diagram must show internal structure, not just a hub. See diagram rules below.
- Limit the report to what a teammate needs to understand the branch quickly. Avoid raw diff paraphrasing.
Mermaid diagram rules
The Change Map must be an expanded, detailed flowchart that shows:
- Each logical change area as a subgraph with its internal nodes (key changed symbols, screens, use cases, contracts, or data steps).
- The data or control flow between nodes within each subgraph.
- Cross-area dependencies as labeled edges between subgraphs.
- The overall branch intent as a root node.
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 · 225 lines · 50 tokens per session scan A 4c77f4466103
change-intent-synthesizer is an agent published in the GitHub repository leenspace/contextur (7 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 1,643 once invoked, about $0.0003 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.