Borrowing it
Nothing to install: this file belongs to utilitydelta/mcp-graph-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/utilitydelta/mcp-graph-engine/main/.claude/agents/diff-analyzer.mdgit clone --depth 1 https://github.com/utilitydelta/mcp-graph-engineWrote 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/utilitydelta/mcp-graph-engine/diff-analyzer)<a href="https://agentmods.dev/agents/utilitydelta/mcp-graph-engine/diff-analyzer"><img src="https://agentmods.dev/badge/agents/utilitydelta/mcp-graph-engine/diff-analyzer/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/utilitydelta/mcp-graph-engine/diff-analyzer"><img src="https://agentmods.dev/badge/agents/utilitydelta/mcp-graph-engine/diff-analyzer.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 | $0.00025 | $0.00358 |
| Opus 5.5 | $0.00010 | $0.00143 |
| Sonnet 5.5 | $0.00005 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
diff-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 2mo 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.
What it actually says
Diff Analyzer
Analyze git diffs and extract structural changes for replay guide generation.
Your Task
Given a git diff (base commit to HEAD), extract:
1. Structural Changes
For Rust projects:
- New modules (
moddeclarations) - Public types (structs, enums, type aliases)
- Trait definitions
- Impl blocks
- Public functions
- Modified signatures
For other languages, adapt to equivalent constructs.
2. Dependencies
- Type A uses Type B
- Function X depends on Function Y
- Import/use relationships
- Trait bounds and implementations
3. Change Classification
For each file:
| Classification | Meaning |
|---|---|
| NEW | Entirely new file |
| EXTENDED | New items added to existing |
| MODIFIED | Existing items changed |
| REFACTORED | Structure changed, behavior same |
| DELETED | Removed |
Output Format
Return structured data:
## Files Changed
| File | Classification | Summary |
|------|----------------|---------|
| ... | ... | ... |
## New Types
- `TypeName` in `path/file.rs` — {description}
## New Functions
- `fn_name()` in `path/file.rs` — {description}
## Dependencies
- `TypeA` depends on `TypeB`
- `fn_x()` calls `fn_y()`
## Notes
- {anything unusual or noteworthy}
Keep output concise. The orchestrator will use this for clustering.
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.
- 2mo ago First seen · 71 lines · 25 tokens per session scan A 33cc484c4782
diff-analyzer is an agent published in the GitHub repository utilitydelta/mcp-graph-engine (6 stars, last pushed 9mo ago), licensed MIT. It adds 25 tokens to every session and 358 once invoked, about $0.0001 per session on Opus 5.5. 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
unbloat-remediator
Orchestrate safe bloat remediation - execute deletions, refactorings, consolidations, and archiving with user approval. Creates backups, runs tests, provides rollback.
phoenix-bug-fixer
Leads one Phoenix bug from report to draft PR - reproduce, fix, review, revise.
git-investigator
Code archaeology expert. Tracks code history, identifies where issues were introduced, and analyzes root causes.
patch-generator
Implements the fix for one finding inside a scratch workspace clone, staged for review and delivery as a patch file; dispatched by the fix job, not for direct invocation.
git-historian
Use this agent for git archaeology, when the user asks "why does this code exist", "when did this break", "what introduced this behavior", mentions "git blame", "git bisect", "pickaxe", "regression", "who changed this", or "find the commit that". Examples.
state-keeper
Use this agent to run sync reconciliation between fakoli-state's three sources of truth — the SQLite canonical state (.fakoli-state/state.db), the filesystem (packets/, .evidence-buffer/, worktrees), and git (branches, commits, claims). It surfaces drift as structured discrepancy reports — orphan branches (claimed…