buddy-agent-harness 0.18.0 → 0.19.0
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/.claude-plugin/plugin.json +1 -1
- package/.codex-plugin/plugin.json +1 -1
- package/.cursor-plugin/plugin.json +1 -1
- package/dist/cli.mjs +42 -13
- package/dist/index.d.mts +12 -5
- package/dist/index.d.mts.map +1 -1
- package/dist/index.mjs +42 -13
- package/dist/index.mjs.map +1 -1
- package/dist/skill-scripts/doctor.mjs +39 -39
- package/dist/skill-scripts/init.mjs +39 -39
- package/dist/skill-scripts/mcp.mjs +39 -39
- package/dist/skill-scripts/reference.mjs +39 -39
- package/package.json +1 -1
- package/plugin.json +1 -1
- package/skills/doctor-buddy-agent-harness/SKILL.md +1 -1
- package/skills/doctor-buddy-agent-harness/references/global-instructions.md +4 -1
- package/skills/doctor-buddy-agent-harness/references/harnesses/claude-code.md +1 -1
- package/skills/doctor-buddy-agent-harness/references/harnesses/codex.md +1 -1
- package/skills/doctor-buddy-agent-harness/references/harnesses/copilot-cli.md +1 -1
- package/skills/doctor-buddy-agent-harness/scripts/doctor.mjs +39 -39
- package/skills/enhance/SKILL.md +2 -1
- package/skills/enhance/scripts/doctor.mjs +39 -39
- package/skills/init-buddy-agent-harness/SKILL.md +1 -1
- package/skills/init-buddy-agent-harness/scripts/doctor.mjs +39 -39
- package/skills/init-buddy-agent-harness/scripts/init.mjs +39 -39
- package/skills/reference/SKILL.md +1 -1
- package/skills/reference/scripts/reference.mjs +39 -39
- package/skills/repair/SKILL.md +2 -2
- package/skills/repair/scripts/doctor.mjs +39 -39
- package/skills/repair/scripts/mcp.mjs +39 -39
- package/src/diagnose-bridges/diagnose-bridges.ts +1 -1
- package/src/diagnose-bridges/diagnose-global-instructions.ts +29 -11
- package/src/diagnose-bridges/doctor-guidance.ts +25 -2
- package/src/harness-registry/harness-registry.ts +7 -0
package/package.json
CHANGED
package/plugin.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
|
|
3
3
|
"name": "buddy-agent-harness",
|
|
4
|
-
"version": "0.
|
|
4
|
+
"version": "0.19.0",
|
|
5
5
|
"description": "Initialize standards-based agent configuration across agent harnesses",
|
|
6
6
|
"author": {
|
|
7
7
|
"name": "repobuddy"
|
|
@@ -17,7 +17,7 @@ Diagnose it:
|
|
|
17
17
|
node scripts/doctor.mjs
|
|
18
18
|
```
|
|
19
19
|
|
|
20
|
-
That path is relative to this skill's own directory: `scripts/doctor.mjs` is a self-contained bundle built from this package's source and shipped inside the skill folder through the npm package, so it runs against the current working directory with nothing downloaded and no `node_modules` needed. Fall back to `npx -y buddy-agent-harness@^0.
|
|
20
|
+
That path is relative to this skill's own directory: `scripts/doctor.mjs` is a self-contained bundle built from this package's source and shipped inside the skill folder through the npm package, so it runs against the current working directory with nothing downloaded and no `node_modules` needed. Fall back to `npx -y buddy-agent-harness@^0.19.0 doctor` when `scripts/doctor.mjs` is missing or cannot be run — the case for a skill installed from git rather than from the npm package, which does not carry the bundle.
|
|
21
21
|
|
|
22
22
|
The command is read-only. It never repairs anything, so it is safe to run at any point, including from a session-start hook.
|
|
23
23
|
|
|
@@ -13,13 +13,14 @@
|
|
|
13
13
|
|
|
14
14
|
Cursor keeps its user rules in a settings panel rather than a file, so there is nothing on disk to check; Devin Desktop documents no user-scope path. Neither gets a row.
|
|
15
15
|
|
|
16
|
-
A harness's directory can be moved by a variable: `CLAUDE_CONFIG_DIR` for `claude-code` (`~/.claude`), `CODEX_HOME` for `codex` (`~/.codex`), `COPILOT_HOME` for `copilot-cli` (`~/.copilot`). Where one is set and non-empty, the row and the step name the file under it, written from the variable — `$CODEX_HOME/AGENTS.md` — so the step works in the shell the user ran `doctor` from.
|
|
16
|
+
A harness's directory can be moved by a variable: `CLAUDE_CONFIG_DIR` for `claude-code` (`~/.claude`), `CODEX_HOME` for `codex` (`~/.codex`), `COPILOT_HOME` for `copilot-cli` (`~/.copilot`). Where one is set and non-empty, the row and the step name the file under it, written from the variable — `$CODEX_HOME/AGENTS.md` — so the step works in the shell the user ran `doctor` from. Set but empty, it is read the way the harness reads it: as unset for `CODEX_HOME` and `COPILOT_HOME`, and as the directory the harness starts in for `CLAUDE_CONFIG_DIR`.
|
|
17
17
|
|
|
18
18
|
| Finding | What it means | Repair |
|
|
19
19
|
| --- | --- | --- |
|
|
20
20
|
| `global-instructions-missing` | no user-scope instruction file at this path — the harness loads none of ~/.agents/AGENTS.md | hand the user the step the harness page names for that file; write nothing yourself |
|
|
21
21
|
| `global-instructions-unbridged` | the file holds its own content and does not load ~/.agents/AGENTS.md — text placed there reaches no session of this harness | hand the user the step the harness page names for that file, keeping what the file says; write nothing yourself |
|
|
22
22
|
| `global-instructions-overridden` | the harness reads this file in place of its own user-scope file, so whatever that file loads goes unread, and this one does not load ~/.agents/AGENTS.md | hand the user the move of what that file says into the global file, and its removal; write nothing yourself |
|
|
23
|
+
| `global-instructions-emptied` | the variable is set but empty, which this harness reads as the directory it starts in rather than as unset — its user-scope file is whichever one sits there, not the one in its own folder | hand the user the step of unsetting that variable; write nothing yourself |
|
|
23
24
|
|
|
24
25
|
**Hand the step over; never take it.** The file is in the user's home directory, outside the repository this tool works in, so every repair carries an empty `command` and names the step for the user to take themselves.
|
|
25
26
|
|
|
@@ -27,4 +28,6 @@ A harness's directory can be moved by a variable: `CLAUDE_CONFIG_DIR` for `claud
|
|
|
27
28
|
|
|
28
29
|
`overridden` is the quietest. The user-scope file may be bridged perfectly and still go unread, because the harness reads another file in its place: Codex reads `AGENTS.override.md` before `AGENTS.md`, and uses whichever first holds more than whitespace. The finding names that file. Its content moves into `~/.agents/AGENTS.md` before it is removed; where the user-scope file has a problem of its own, that finding is reported beside it, so both steps are handed over at once.
|
|
29
30
|
|
|
31
|
+
`global-instructions-emptied` blames the variable, not a file. A harness that reads an empty variable as the directory it starts in reads its user-scope file from there — in a repository, the project's own file — so the row names that path, relative, from the directory `doctor` ran in. The finding names the variable, and the step is to unset it or set it to the folder meant: editing the file the row names would bridge one directory only, and the project's file rather than the user's.
|
|
32
|
+
|
|
30
33
|
A row is reported for every harness installed for this user, whether or not `~/.agents/AGENTS.md` exists, so a skill handing text over for that file can say which harnesses will load it. A finding is raised only where the file exists and a harness is not loading it.
|
|
@@ -23,7 +23,7 @@ Described, never written: `init` works inside a repository, and `doctor` reads o
|
|
|
23
23
|
| detection directory | `.claude` |
|
|
24
24
|
| skills projection | `.claude/skills` — written by `init` |
|
|
25
25
|
| instruction bridge | `.claude/CLAUDE.md` — the line `@~/.agents/AGENTS.md`, which loads `~/.agents/AGENTS.md` |
|
|
26
|
-
| moved by | `CLAUDE_CONFIG_DIR` — set and non-empty, it replaces `.claude`, and every path under it moves with it |
|
|
26
|
+
| moved by | `CLAUDE_CONFIG_DIR` — set and non-empty, it replaces `.claude`, and every path under it moves with it; set but empty, it is read as the directory the harness starts in, so `.claude` is that directory |
|
|
27
27
|
| MCP configuration | none |
|
|
28
28
|
|
|
29
29
|
## Configuration only this harness reads
|
|
@@ -22,7 +22,7 @@ Described, never written: `init` works inside a repository, and `doctor` reads o
|
|
|
22
22
|
| detection directory | `.codex` |
|
|
23
23
|
| skills projection | none — reads `.agents/skills` natively |
|
|
24
24
|
| instruction bridge | `.codex/AGENTS.md` — a symlink to `~/.agents/AGENTS.md`, since no import this file supports reaches it |
|
|
25
|
-
| moved by | `CODEX_HOME` — set and non-empty, it replaces `.codex`, and every path under it moves with it |
|
|
25
|
+
| moved by | `CODEX_HOME` — set and non-empty, it replaces `.codex`, and every path under it moves with it; set but empty, it is read as unset |
|
|
26
26
|
| suppresses `AGENTS.md` | `.codex/AGENTS.override.md` — this harness reads `AGENTS.md` itself, and reads one of these instead where it finds one |
|
|
27
27
|
| MCP configuration | none |
|
|
28
28
|
|
|
@@ -22,7 +22,7 @@ Described, never written: `init` works inside a repository, and `doctor` reads o
|
|
|
22
22
|
| detection directory | `.copilot` |
|
|
23
23
|
| skills projection | none — reads `.agents/skills` natively |
|
|
24
24
|
| instruction bridge | `.copilot/copilot-instructions.md` — a symlink to `~/.agents/AGENTS.md`, since no import this file supports reaches it |
|
|
25
|
-
| moved by | `COPILOT_HOME` — set and non-empty, it replaces `.copilot`, and every path under it moves with it |
|
|
25
|
+
| moved by | `COPILOT_HOME` — set and non-empty, it replaces `.copilot`, and every path under it moves with it; set but empty, it is read as unset |
|
|
26
26
|
| MCP configuration | none |
|
|
27
27
|
|
|
28
28
|
## Configuration only this harness reads
|