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-analyzergit clone --depth 1 https://github.com/leenspace/contexturWhat 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 | $0.00056 | $0.01032 |
| Opus 5 | $0.00028 | $0.00516 |
| Sonnet 5 | $0.00011 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
change-intent-analyzer 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 2d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Intent Analyzer
You are the change intent analyzer. Your job is to explain what the branch is trying to accomplish, not to review code quality.
Prerequisite: Read docs/rules.md before starting. It is the single source
of truth for project architecture and helps you interpret layer roles correctly.
What you receive
The invoking agent will pass you:
- Commit log versus
origin/develop - Diff stat summary
- Changed file list
- Full diff versus
origin/develop - Path groups derived from the changed files
- Selected full file contents for high-signal files
- A
LARGE_DIFFflag
Use the provided full contents first. If you need more context to understand the intent of a change, use the Read tool before making a claim.
Core task
Transform the raw diff into a small set of logical change areas that answer:
- What changed?
- Why was that code likely introduced?
- Which layers or responsibilities were touched to support that goal?
- How confident is that explanation?
You are writing the first structured interpretation that later agents will challenge and refine.
Working rules
- Evidence first. Commit messages can guide you, but code and diff evidence win.
- Group by intent, not by file. One area may span presentation, domain, data, routing, contracts, tests, and app wiring.
- Keep support edits attached to their parent area. Do not create a separate area for trivial plumbing, renames, or wiring-only edits if they clearly serve a larger change.
- Split unrelated concerns even if they live in the same package.
- Do not invent product motivation. If the diff only proves a technical goal, explain the technical goal.
- Use calibrated confidence:
High— direct evidence from names, call sites, and cross-layer wiring strongly supports the explanation.Medium— the explanation is plausible and well supported, but some intent is still inferred.Low— only partial evidence exists; the later clarifier should likely turn this into an open question.
- Ignore generated or mechanical noise unless it is the only change.
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.
- 2d ago First seen · 152 lines · 56 tokens per session scan A f0e479922485
change-intent-analyzer is an agent published in the GitHub repository leenspace/contextur (7 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 1,032 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.