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 commands/samuel0101010/wisp-agentdiff/review-agentsgit 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 | $0.00018 | $0.00445 |
| Opus 5 | $0.00009 | $0.00222 |
| Sonnet 5 | $0.00004 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
review-agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the wisp-agentdiff review TUI in the current working directory.
Preferred (plugin-bundled binary, no PATH or npm install required):
node "${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:
- Run
node "${CLAUDE_PLUGIN_ROOT}/dist/index.js" doctor --repo .— this checks git repo, binary, manifest, state file, skill registration. - If
doctorsays everything is OK / WARN-only, dispatch the bundled canary to fire the hooks once:Task(subagent_type: "wisp-self-test", description: "verify wisp-agentdiff hooks fire", prompt: "go") - Then re-run
/review-agents. You should now see one agentwisp-self-testwith a single-line diff. - If you've been running many sessions and want to clean up the accumulated worktrees + branches, run
node "${CLAUDE_PLUGIN_ROOT}/dist/index.js" prune --dry-runto see candidates, then drop--dry-runto execute.
If the canary runs but state still doesn't update, the WorktreeCreate hook isn't firing — open an issue with the doctor output.
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 · 35 lines · 18 tokens per session scan A a976ddf24095
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.