@uge/payo 2.4.8 → 2.5.0
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.
- package/README.md +26 -3
- package/dist/index.js +214 -206
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -300,7 +300,7 @@ One universal layout, whichever agent CLI you pick — no per-tool formats:
|
|
|
300
300
|
| ------------------------------- | ------------------------------------------------------------------ |
|
|
301
301
|
| `AGENTS.md` | The entrypoint most tools read natively — your project's base rules |
|
|
302
302
|
| `.agents/skills/<id>/SKILL.md` | One [Agent Skill](https://agentskills.io) per topic, spec frontmatter |
|
|
303
|
-
| `CLAUDE.md` | A one-line `@AGENTS.md` import shim
|
|
303
|
+
| `CLAUDE.md` | A one-line `@AGENTS.md` import shim for Claude Code < 2.1.281 |
|
|
304
304
|
| `.claude/skills/**` | Symlinks into `.agents/skills/` (dir copy on Windows) for Claude Code |
|
|
305
305
|
| `.windsurf/skills/**` | The same shim for Windsurf |
|
|
306
306
|
|
|
@@ -308,8 +308,11 @@ Who reads what, with no extra work:
|
|
|
308
308
|
|
|
309
309
|
- **Codex, Cursor, Copilot, Gemini CLI, Antigravity, Zed, Devin** → `.agents/skills/`
|
|
310
310
|
and `AGENTS.md` natively.
|
|
311
|
-
- **Claude Code** → the
|
|
312
|
-
|
|
311
|
+
- **Claude Code** → the `.claude/skills/` symlinks (officially supported; it
|
|
312
|
+
dedupes if it also reads the target directly), plus `AGENTS.md` natively from
|
|
313
|
+
2.1.281. On older versions Payo also writes the `CLAUDE.md` shim. Payo checks
|
|
314
|
+
the installed version, and always writes the shim if a `CLAUDE.md` already
|
|
315
|
+
exists, since Claude Code then reads that file instead.
|
|
313
316
|
- **Windsurf** → `AGENTS.md` plus the `.windsurf/skills/` shim.
|
|
314
317
|
|
|
315
318
|
> **Zed users:** Zed reads only the **first** instruction file it finds, in the order
|
|
@@ -328,6 +331,23 @@ agent uses it at that point to check your pending change against the relevant pr
|
|
|
328
331
|
skills and flag anything that conflicts. It reads the diff and reports — it never runs
|
|
329
332
|
your tests, linter or formatter, because your git hook already does.
|
|
330
333
|
|
|
334
|
+
Payo can also add a **pr-review** skill (`.agents/skills/pr-review/SKILL.md`) if you
|
|
335
|
+
opt in. Your assistant uses it when you ask for a review of your local changes, the
|
|
336
|
+
current branch, or a PR / MR by number. Before it reads any code, it asks what to focus
|
|
337
|
+
on (bugs, security, code quality, tests), which level of findings you want, and whether
|
|
338
|
+
to check the change against your project skills. In Claude Code that is one
|
|
339
|
+
`AskUserQuestion` prompt. It checks each finding against the surrounding code before
|
|
340
|
+
reporting it, labels it the [Conventional Comments](https://conventionalcomments.org/)
|
|
341
|
+
way (`issue (blocking):`, `suggestion:`, `nitpick:`, and so on), and puts the worst
|
|
342
|
+
first. Then you pick what happens next: stop, let it fix the issues in your own change,
|
|
343
|
+
post one review on the PR / MR, or get inline comments to paste yourself.
|
|
344
|
+
|
|
345
|
+
It fetches a PR with plain git into a temporary ref, and never checks it out or runs its
|
|
346
|
+
code. It needs `gh` or `glab` only to read a PR description or to post, and it never
|
|
347
|
+
approves a PR or requests changes. Claude Code's `/code-review` and Codex's `/review`
|
|
348
|
+
are built-in commands, so typing them runs those instead. Ask in words ("review PR 42")
|
|
349
|
+
or type `/pr-review`.
|
|
350
|
+
|
|
331
351
|
### Guardrails enforced by hooks, not just prose
|
|
332
352
|
|
|
333
353
|
Skills are guidance the assistant _should_ follow — but an agent can skip prose. So
|
|
@@ -403,6 +423,9 @@ your stack needs. Dimensions covered:
|
|
|
403
423
|
every push)
|
|
404
424
|
- **Change audit** _(optional)_ — opt into a skill that checks your pending
|
|
405
425
|
change against the project skills before commit or push
|
|
426
|
+
- **Code review** _(optional)_: opt into a skill for on-demand reviews, then set
|
|
427
|
+
the team defaults: what you review, which focus areas to recommend, how findings
|
|
428
|
+
read, and a team checklist every review checks
|
|
406
429
|
|
|
407
430
|
## AI vs. template generation
|
|
408
431
|
|