What is agentdiff CLAUDE.md?

A project guide for agentdiff, a Rust and Python command-line tool that records which AI agent wrote which lines in a Git repository. It describes how events become signed attribution records.

Use it when capturing agent activity, preparing or finalizing attribution during commits, building the tool, or reading its reports and trace files.

It explains the tracking pipeline and its storage rules, helping changes preserve reliable authorship records.

agentdiff CLAUDE.md — Instructions file by codeprakhar25

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 instructions/codeprakhar25/agentdiff/claude-md

Clone the repo

git clone --depth 1 https://github.com/codeprakhar25/agentdiff

Per session 391 This file is loaded in full into every session.

When invoked 391 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00391	$0.00391
Opus 5	$0.00196	$0.00196
Sonnet 5	$0.00078	$0.00078
Haiku 4.5	$0.00039	$0.00039

Measured 2d ago against content hash 1537078b24e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentdiff CLAUDE.md 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.

CLAUDE.md · 18 lines

What it actually says

agentdiff — Project Context for Claude

Project summary

agentdiff is a Rust + Python CLI that tracks which AI agent (claude-code, cursor, opencode, copilot, etc.) wrote which lines of code in a git repo. It hooks into agent tool callbacks, captures to session.jsonl, then on commit runs prepare-ledger.py → finalize-ledger.py to produce signed AgentTrace records in .git/agentdiff/traces/{branch}.jsonl.

Architecture

Capture: per-agent Python scripts (capture-claude.py, etc.) write raw events to .git/agentdiff/session.jsonl
Prepare (scripts/prepare-ledger.py): runs pre-commit, reads session.jsonl, computes per-file attribution using line overlap, writes pending_ledger.json
Finalize (scripts/finalize-ledger.py): runs post-commit, converts pending payload to signed AgentTrace, appends to traces/{branch}.jsonl
Store (src/store.rs): reads traces into Entry structs for list / report commands
Binary install path: ~/.local/bin/agentdiff (NOT ~/.cargo/bin/) — always cp target/release/agentdiff ~/.local/bin/agentdiff after build

Attribution invariants

copilot is in _EXCLUDED_AGENTS — captured in session.jsonl for stats, never wins file attribution
Files with no session evidence → agent = "human", must be explicit in attribution dict
agent = "human" in payload is the semantic token; git_author holds the display name
contributor.type = "human" iff file_agent == "human" — never infer from tool name

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.

2d ago First seen · 18 lines · 391 tokens per session scan A 1537078b24e3

Subscribe to this mod's changes

agentdiff CLAUDE.md is an instructions file published in the GitHub repository codeprakhar25/agentdiff (43 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 391 tokens to every session, about $0.0020 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 2026-08-30.

Git and workflow Languages Planning attribution claude-code copilot cursor developer-tools

gortex CLAUDE.md

Instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).

zzet/gortex · 5,172 tokens

mcp-unity AGENTS.md

Instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).

CoderGamester/mcp-unity · 2,498 tokens

mcp-server-azure-devops AGENTS.md

Instructions for Tiberriver256/mcp-server-azure-devops: /home/tiberriver256/repos/mcp-server-azure-devops/docs/important-knowledge/azure-devops-rest-api-research.md Researching Azure DevOps REST APIs, selecting api-version, or handling Azure DevOps Server (on-prem) endpoints.

Tiberriver256/mcp-server-azure-devops · 178 tokens

rosetta AGENTS.md

Instructions for griddynamics/rosetta: Main goal: cover E2E AI PDLC engineering workflows at foundation level for AI-First SDLC in enterprise. Top-level or orchestrator agents MUST READ docs/ARCHITECTURE.md contains technical details and guidance, and docs/CONTEXT.md - business context. Subagents - when needed.…

griddynamics/rosetta · 270 tokens

rails-ai-context AGENTS.md

Instructions for crisnahine/rails-ai-context, covering rails-ai-context, agent skills, issue tracker, triage labels and domain docs.

crisnahine/rails-ai-context · 134 tokens

inspecto CLAUDE.md

Instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.

inspecto-dev/inspecto · 1,014 tokens