review-agents

A terminal interface for reviewing the separate code changes made by different agents in a session. It shows each agent’s changes, usage summary, and conflicts between changes.

In plain words
What is it for?
Use it to review agent-generated code, move between agents, inspect conflicts, approve or revert changes, and merge approved work.
Why use it?
It gives you a place to inspect, approve, reject, and combine agent work before it becomes part of the project.

Command

Part of the wisp-agentdiff plugin — 1 skill, 1 command, 1 agent, 3 hooks shipped together

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 commands/samuel0101010/wisp-agentdiff/review-agents
Clone the repo
git clone --depth 1 https://github.com/Samuel0101010/wisp-agentdiff

Or install wisp-agentdiff, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent, 3 hooks.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 445 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 $0.00018 $0.00445
Opus 5 $0.00009 $0.00222
Sonnet 5 $0.00004 $0.00089
Haiku 4.5 $0.00002 $0.00044

Measured 2d ago against content hash a976ddf24095, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-agents 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.

commands/review-agents.md · 35 lines

What it actually says

Run the wisp-agentdiff review TUI in the current working directory.

Preferred (plugin-bundled binary, no PATH or npm install required):

node "${CLAUDE_PLUGIN_ROOT}/dist/index.js" review --repo .

Fallback (when the user installed via npm i -g wisp-agentdiff instead):

wisp-agentdiff review

The TUI lists every subagent the current Claude Code session recorded, with per-agent diff, token + tool-call summary, and cross-agent conflict detection.

Hotkeys: a approve · r revert · n/p next/prev agent · c toggle conflict view · m merge approved · j/k scroll · q quit.

If the TUI says "no subagents recorded"

The plugin only captures subagents that were spawned with isolation: worktree in their definition. If /review-agents shows the empty-state message:

  1. Run node "${CLAUDE_PLUGIN_ROOT}/dist/index.js" doctor --repo . — this checks git repo, binary, manifest, state file, skill registration.
  2. If doctor says everything is OK / WARN-only, dispatch the bundled canary to fire the hooks once: Task(subagent_type: "wisp-self-test", description: "verify wisp-agentdiff hooks fire", prompt: "go")
  3. Then re-run /review-agents. You should now see one agent wisp-self-test with a single-line diff.
  4. If you've been running many sessions and want to clean up the accumulated worktrees + branches, run node "${CLAUDE_PLUGIN_ROOT}/dist/index.js" prune --dry-run to see candidates, then drop --dry-run to execute.

If the canary runs but state still doesn't update, the WorktreeCreate hook isn't firing — open an issue with the doctor output.

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 · 35 lines · 18 tokens per session scan A a976ddf24095

Subscribe to this mod's changes

review-agents is a command published in the GitHub repository Samuel0101010/wisp-agentdiff (2 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 445 once invoked, about $0.0001 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.