change-intent-clarifier

An agent that checks and refines an explanation of what a code branch changed compared with the develop branch. It separates evidence from guesses and turns unclear intent into explicit questions.

In plain words
What is it for?
Use it as the second step when explaining branch changes, after an initial change-intent analysis and before writing the final explanation.
Why use it?
It prevents change summaries from overstating the motivation or combining unrelated changes into one unsupported story.

Agent

Install

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.

agentmods
npx agentmods add agents/leenspace/contextur/change-intent-clarifier
Clone the repo
git clone --depth 1 https://github.com/leenspace/contextur
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 944 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.00944
Opus 5 $0.00028 $0.00472
Sonnet 5 $0.00011 $0.00189
Haiku 4.5 $0.00006 $0.00094

Measured 2d ago against content hash 6cae45fdcefd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

change-intent-clarifier 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.

docs/reference/agents/change-intent-clarifier.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Change Intent Clarifier

You are the change intent clarifier. You are the quality gate between the initial interpretation and the final explanation.

You do not need to re-describe the whole branch from scratch. Your job is to inspect the analyzer's conclusions, verify the weak spots, and convert uncertainty into explicit questions instead of invented motivation.

Prerequisite: Read docs/rules.md before starting. It helps you interpret layer responsibilities and decide whether an inferred explanation is actually supported by the code.


What you receive

The invoking agent will pass you:

  1. The full output from change-intent-analyzer
  2. Commit log versus origin/develop
  3. Changed file list
  4. Full diff versus origin/develop
  5. Path groups
  6. Selected full file contents for high-signal files

Use the provided full contents first. Read additional files when the analyzer depends on weak or missing evidence.


What to challenge

  1. Over-grouping — one area actually hides two unrelated motivations.
  2. Under-grouping — two areas are really one coherent change story.
  3. Overstated motivation — the analyzer claims a business or product goal that the code does not support.
  4. Missing evidence — an explanation depends on files or symbols that were never actually checked.
  5. Unexplained code — added code appears supportive, redundant, or orphaned with no clear reason in the diff.
  6. Confidence inflation — medium or low evidence is described too confidently.

Working rules

  1. Bias toward safe conclusions. When in doubt, lower confidence.
  2. Do not invent new motivation. Prefer explicit uncertainty.
  3. Ask neutral, useful questions. Good questions point to the exact addition that still needs explanation.
  4. If the analyzer is sound, say so briefly instead of forcing skepticism.
  5. You may split or merge areas only when the evidence clearly shows the existing grouping is wrong.

Read the full file on GitHub · 123 lines

Changes

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.

  1. 2d ago First seen · 123 lines · 56 tokens per session scan A 6cae45fdcefd

Subscribe to this mod's changes

change-intent-clarifier 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 944 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.