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/proxy2021/enso/enso-testgit clone --depth 1 https://github.com/Proxy2021/EnsoWhat 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 | $0.00000 | $0.01957 |
| Opus 5 | $0.00000 | $0.00979 |
| Sonnet 5 | $0.00000 | $0.00391 |
| Haiku 4.5 | $0.00000 | $0.00196 |
Grade A, and why
enso-test scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **Plugin server**: `curl -sf http://localhost:3001/health` → must return `{"ok":true}` How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comprehensive live end-to-end test of the Enso platform. Tests infrastructure, backend, and frontend features in the browser with strict pass/fail criteria.
Prerequisites: Chrome MCP (Claude in Chrome) must be connected for Phase 4 browser tests. Enso services must be running (
./restart.shif not).
Approach: If any tests fail, list all failures with root causes and recommend specific fixes. The user can then enter plan mode to address issues before re-testing.
Phase 1 — Infrastructure Health
Verify all services are running. If any fail here, stop and tell the user to run ./restart.sh first.
- Plugin server:
curl -sf http://localhost:3001/health→ must return{"ok":true} - Vite dev server:
curl -sf -o /dev/null -w '%{http_code}' http://localhost:5173→ must be200 - Version endpoint:
curl -sf http://localhost:3001/api/version→ must return valid JSON withversionCodefield - Action log:
curl -sf "http://localhost:3001/api/action-log?count=5"→ must return JSON array - WebSocket: Write a quick Node script to verify WS connection:
Ifnode -e " const ws = new (require('ws'))('ws://localhost:3001/ws'); ws.on('open', () => { console.log('WS_OK'); ws.close(); process.exit(0); }); ws.on('error', (e) => { console.log('WS_FAIL:', e.message); process.exit(1); }); setTimeout(() => { console.log('WS_TIMEOUT'); process.exit(1); }, 5000); "wsmodule not available, skip this check with a note.
Record the current timestamp before proceeding — you'll use it in Phase 5 to filter new errors.
Phase 2 — Backend Unit Tests
Run the Vitest test suite:
npx vitest run --reporter=verbose 2>&1
Pass criteria: All tests pass (exit code 0). Report X/Y passed. If any fail, log the failure details but continue testing.
Phase 3 — TypeScript Compilation
Run both server and frontend type checks:
npx tsc -p tsconfig.server.json --noEmit 2>&1
npx tsc --noEmit 2>&1
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.
- yesterday First seen · 168 lines · 0 tokens per session scan A 2e3223519084
enso-test is a command published in the GitHub repository Proxy2021/Enso (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,957 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
release
Before publishing, run the compatibility bootstrap.
story-short-scan
短篇网文扫榜。分析知乎盐言、番茄短篇等平台热门数据。.
audit_docs
Audit all project metadata files for stale counts, version mismatches, broken references, and missing entries. Reports discrepancies without auto-fixing.
tma1-peer
List recent sessions on this project by agent — peers (Codex, OpenClaw, Copilot CLI) or your own.
merge_session
Merge session branch(es) into main via rebase + fast-forward push. Use from inside a session worktree pane to land your work, or with --all to batch merge all sessions from the main repo.
implement
Start implementing a Linear ticket by creating a branch and entering plan mode.