Borrowing it
Nothing to install: this file belongs to sandeep-alluru/agentdelta. 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/sandeep-alluru/agentdelta/main/CLAUDE.mdgit clone --depth 1 https://github.com/sandeep-alluru/agentdeltaWrote 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/instructions/sandeep-alluru/agentdelta/claude-md)<a href="https://agentmods.dev/instructions/sandeep-alluru/agentdelta/claude-md"><img src="https://agentmods.dev/badge/instructions/sandeep-alluru/agentdelta/claude-md.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 5.1 | $0.00830 | $0.00830 |
| Opus 5 | $0.00415 | $0.00415 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
agentdelta 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 6d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentdelta — Developer Guide
agentdelta is a semantic diff engine for AI agent behavior. It records step-by-step agent traces as JSONL, embeds nodes with all-MiniLM-L6-v2, aligns two traces by cosine similarity, and detects the first semantic fork point.
Architecture
trace.py Data model: NodeType, EdgeType, TraceNode, TraceEdge, AgentTrace
embed.py sentence-transformers singleton + sliding-window alignment
diff.py Fork detection → DiffResult, ForkPoint, StepDiff
instrument.py LangChain callback (AgentdeltaCallback) + record() context manager
report.py Rich terminal / JSON / Markdown output formatters
cli.py Click CLI: `agentdelta diff` and `agentdelta inspect`
See ARCHITECTURE.md for full data flow and algorithm details.
Setup
git clone https://github.com/sandeep-alluru/agentdelta
cd agentdelta
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
pre-commit install
Development commands
make test # pytest with branch coverage (fails under 85%)
make lint # ruff check + format check
make typecheck # mypy --strict
make fmt # ruff format (auto-fix)
make all # lint + typecheck + test
Running tests
pytest # all 43 tests
pytest tests/test_diff.py -v # single module
pytest -k "test_fork" # by name
Key invariants
TraceNode.idis content-addressed (SHA-256[:16] of{node_type}:{content}). Same content = same ID across runs.embed_trace()mutates nodes in-place and is idempotent — safe to call twice.align_traces()uses greedy 1:1 matching, O(n·window). Default window=5.fork_threshold=0.70: first aligned pair below this becomes theForkPoint.match_threshold=0.85: pairs above this are "match" (no change).has_regressionis True ifffork_point is not None.
Adding a new output format
- Add a
to_<format>(result: DiffResult) -> strfunction inreport.py - Add the format name to the
--formatchoice incli.py - Add tests in
tests/test_report.py
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.
- 6d ago First seen · 85 lines · 830 tokens per session scan A bf0bfadf8619
agentdelta CLAUDE.md is an instructions file published in the GitHub repository sandeep-alluru/agentdelta (0 stars, last pushed 19d ago), licensed MIT. It adds 830 tokens to every session, about $0.0042 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.