@uge/payo 2.3.0 → 2.3.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +24 -14
  2. package/dist/index.js +213 -205
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -253,7 +253,8 @@ present.
253
253
  Optionally, Payo adds a **change-audit** skill (`.agents/skills/change-audit/SKILL.md`):
254
254
  if you opt in, it asks when to run — before every commit or before pushing — and the
255
255
  agent uses it at that point to check your pending change against the relevant project
256
- skills and flag anything that conflicts.
256
+ skills and flag anything that conflicts. It reads the diff and reports — it never runs
257
+ your tests, linter or formatter, because your git hook already does.
257
258
 
258
259
  ### Guardrails enforced by hooks, not just prose
259
260
 
@@ -261,21 +262,30 @@ Skills are guidance the assistant _should_ follow — but an agent can skip pros
261
262
  when you enable a guardrail, Payo also writes the hook that makes it fire regardless:
262
263
 
263
264
  - **A git hook (mechanical, hard block).** When you turn on the gitleaks scan or the
264
- verify-before-commit/push step, Payo writes a **`lefthook.yml`** (or, if your repo
265
- already uses **husky**, **pre-commit**, or native `.git/hooks`, merges into _that_
266
- runner instead — never clobbering your setup). It runs `gitleaks` and your test
267
- command at the stage you chose and **blocks the commit/push on failure** — for every
268
- tool, and for a human typing `git`. Payo writes the config; you wire it up once with
269
- `lefthook install` (Payo tells you the command; it installs nothing itself).
270
- - **A native tool hook (soft confirm).** For **Claude, Cursor, and Copilot**, Payo
271
- writes a `PreToolUse` hook that pops a **confirm prompt** right when the agent runs
272
- `git commit` / `git push` (to run change-audit or confirm the push) or a destructive
273
- query (DB-safety). It stores no state and runs no model — it just makes the prompt
274
- appear so the guardrail isn't silently skipped. Tools without a soft-confirm hook
275
- (Codex, Antigravity, Windsurf) are covered by the git hook above.
265
+ verify-before-commit/push step, Payo writes a **`lefthook.yml`** running `gitleaks`,
266
+ your test command, your linter and a format check at the stage you chose, and
267
+ **blocking the commit/push on failure** — for every tool, and for a human typing
268
+ `git`. Payo writes the config; you wire it up once with `lefthook install` (Payo
269
+ tells you the command; it installs nothing itself).
270
+
271
+ **If your repo already has hooks** — **lefthook**, **husky**, **pre-commit**,
272
+ **simple-git-hooks** or native `.git/hooks` — Payo reads what each stage already
273
+ runs and, by default, **leaves your setup completely untouched**. Anything it
274
+ already covers is simply never added; for anything missing, Payo asks whether to
275
+ append it or leave the file alone, and leaving it alone is the recommended answer.
276
+ - **A native tool hook.** For **Claude, Cursor, and Copilot**, Payo writes a
277
+ `PreToolUse` hook that fires when the agent runs `git commit` / `git push` or a
278
+ destructive query. Confirm-push and DB-safety raise a **confirm prompt for you**.
279
+ Change-audit instead **denies the command once** with an instruction back to the
280
+ agent — a confirm prompt would just be approved and the audit skipped — and the
281
+ retry for that same change goes through. It stores nothing outside `.git/` and runs
282
+ no model. Tools without a pre-tool hook (Codex, Antigravity, Windsurf) are covered
283
+ by the git hook above.
276
284
 
277
285
  Both are **idempotent** — re-running Payo never duplicates a hook — and are written
278
- only for the guardrails you actually enabled.
286
+ only for the guardrails you actually enabled. Whatever a hook runs, the generated
287
+ skills tell the agent **not** to run it as well, so the same checks never execute
288
+ twice; anything no hook covers stays an explicit instruction to the agent.
279
289
 
280
290
  The question Payo asks — _"Which agent CLI should Payo use to generate content?"_ —
281
291
  picks only **which installed CLI authors the content**. The output above works with