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 instructions/samuel0101010/wisp-agentdiff/claude-mdgit clone --depth 1 https://github.com/Samuel0101010/wisp-agentdiffWhat 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 | $0.00844 | $0.00844 |
| Opus 5 | $0.00422 | $0.00422 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
wisp-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.
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.
Repo guide for Claude Code
This file is read by Claude Code when working inside this repo. It captures the few conventions that aren't obvious from the source.
What it is
wisp-agentdiff is a TypeScript CLI + Ink TUI that consumes Claude Code's
native WorktreeCreate / WorktreeRemove hooks, captures the diff and
transcript of every subagent worktree, and lets you approve, revert, or
merge each one independently from a tabbed terminal UI.
Full architecture: docs/architecture.md.
Roadmap: docs/roadmap.md.
Module map
| Module | Responsibility |
|---|---|
src/wrap/ |
Worktree manager, pre/post-spawn hook handlers, state file |
src/collect/ |
Unified-diff parser, JSONL transcript reader, per-agent report aggregation |
src/tui/ |
Ink components, pure-reducer hotkey core (hotkeys.ts), run loop |
src/merge/ |
Cross-agent conflict detector, sequential approver |
src/install.ts |
npx wisp-agentdiff install — deploys SKILL + slash command into ~/.claude/ |
templates/ |
Shipped with the npm package: skill.md, review-agents.md, hooks-snippet.json |
tests/ |
Vitest suite — temp git repos for the worktree + merge integration tests |
Build commands
npm install
npm run check # lint + typecheck + test + build (CI-equivalent)
npm run test:watch # iterating on a single module
npm run dev # tsup watch build
The CLI binary is dist/index.js (single ESM file, ~38 KiB). Smoke-test it
without installing globally:
node dist/index.js review --repo .
echo '{"name":"demo"}' | node dist/index.js hook worktree-create --repo .
Conventions
- Edits stay surgical. Match the existing style; no opportunistic refactors in unrelated files. Diff-test every change against the stated task.
- Tests live in
tests/, not co-located. Integration tests that need a real git repo usetests/helpers/temp-repo.ts. - Path normalization. Windows paths must round-trip through
realpathSync.nativebefore string comparison — temp directories can produce short-path forms that don't match what you handed togit. - Hotkey changes go in the reducer, not the App.
tui/hotkeys.tsis pure and unit-tested. The App just dispatches. - No new dependencies without a clear case. The intentional dependency
list is short:
commander,ink,react,simple-git.
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 · 85 lines · 844 tokens per session scan A ccae3623b8b7
wisp-agentdiff CLAUDE.md is an instructions file published in the GitHub repository Samuel0101010/wisp-agentdiff (2 stars, last pushed 3mo ago), licensed MIT. It adds 844 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.