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/try-works/recursive-mode/test-recursive-mode-smokegit clone --depth 1 https://github.com/try-works/recursive-modeWhat 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 | $0.00794 |
| Opus 5 | $0.00000 | $0.00397 |
| Sonnet 5 | $0.00000 | $0.00159 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
test-recursive-mode-smoke 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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
test-recursive-mode-smoke (maintainer command)
Maintainer-facing regression harness for disposable recursive-mode validation.
Usage Pattern
Run recursive-mode smoke tests [quick|full|subagent] [python|powershell|mixed]
Script (Recommended)
python "<REPO_ROOT>/scripts/test-recursive-mode-smoke.py" --scenario quick --toolchain mixed
python "<REPO_ROOT>/scripts/test-recursive-mode-smoke.py" --scenario full --toolchain python --keep-temp
python "<REPO_ROOT>/scripts/test-recursive-mode-smoke.py" --scenario subagent --toolchain mixed
pwsh -NoProfile -File "<REPO_ROOT>/scripts/test-recursive-mode-smoke.ps1" -Scenario quick -Toolchain mixed
pwsh -NoProfile -File "<REPO_ROOT>/scripts/test-recursive-mode-smoke.ps1" -Scenario full -Toolchain powershell -KeepTemp
pwsh -NoProfile -File "<REPO_ROOT>/scripts/test-recursive-mode-smoke.ps1" -Scenario subagent -Toolchain mixed
What It Does
- Creates a disposable temp git repo
- Bootstraps recursive-mode into that repo
- Creates a tiny Python fixture app and a small feature change
- Captures RED and GREEN evidence logs
- Records preflight toolchain decisions, detected executables, and skipped parity paths when applicable
- Scaffolds Phases 4-8 through
recursive-closeoutso late-phase receipts start from the supported helper path - Generates a canonical review bundle
- Locks artifacts through Phase 8 using the supported lock command
- Runs
lint,status, andverify-locks - In
fullmode, runs targeted negative regressions for strict TDD, review bundle validity, context-free reviews, effective-input addenda handling, and QA sign-off requirements - In
subagentmode, proves the dedicated delegated-review path end to end by keeping03.5-code-review.mdbundle-backed andAudit Execution Mode: subagentthrough lock and final closeout - Proves diff audit ignores transient runtime noise such as
__pycache__/and common test caches
Important Safety Property
Every external command is run with an explicit timeout so the harness fails fast instead of hanging indefinitely.
On Windows, run the harness from the real filesystem path rather than from subst or mapped-drive aliases, especially if the evaluated project uses Vite or Vitest.
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.
- 3d ago First seen · 76 lines · 0 tokens per session scan A e3ee105792ee
test-recursive-mode-smoke is a command published in the GitHub repository try-works/recursive-mode (129 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 794 tokens. 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 2026-08-30.
Other commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
debug-playwright
Use this command to debug failing Playwright tests in a source-first, evidence-first workflow.
run-all-tests-and-fix
Execute the full test suite and systematically fix any failures, ensuring code quality and functionality. All test-related commands must pass before completion.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
fd-verify
Verify the implementation — run tests, check regression on affect.md files, review and scan; blocks /fd-done on failure.