plumbbob 0.6.3 → 0.6.4
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/README.md +1 -1
- package/dist/verbs/build.js +7 -0
- package/package.json +1 -1
- package/skills/pb-build/SKILL.md +37 -11
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "plumbbob",
|
|
3
3
|
"displayName": "PlumbBob",
|
|
4
|
-
"version": "0.6.
|
|
4
|
+
"version": "0.6.4",
|
|
5
5
|
"description": "Attention-first build process — driver skills + a CLI that keep you the decider; guidance, not enforcement.",
|
|
6
6
|
"author": { "name": "Rob McLarty", "email": "hello@robmclarty.com", "url": "https://robmclarty.com" },
|
|
7
7
|
"homepage": "https://github.com/robmclarty/plumbbob#readme",
|
package/README.md
CHANGED
|
@@ -121,7 +121,7 @@ nothing else:
|
|
|
121
121
|
| Skill <img alt="" width="110" height="1"> | Does |
|
|
122
122
|
|------------------------------------|------|
|
|
123
123
|
| `/pb-plan` | plan the whole goal — open the session and author intent's Frame, Decisions, Constraints, **and all Steps** |
|
|
124
|
-
| `/pb-build` | implement the next planned step, then verify it to the pause — `--auto` self-approves and chains to done |
|
|
124
|
+
| `/pb-build` | implement the next planned step, then verify it to the pause — `--auto` self-approves and chains to done; a range like `1-3` self-approves through step 3, then pauses |
|
|
125
125
|
| `/pb-finish` | finish up — write the report, make the final commit, clear for a fresh goal |
|
|
126
126
|
|
|
127
127
|
**Plan-shaping moves** — optional, for when the plan needs work mid-flight:
|
package/dist/verbs/build.js
CHANGED
|
@@ -13,6 +13,13 @@ export function build(cwd, args) {
|
|
|
13
13
|
}
|
|
14
14
|
const { build: slug, rest } = resolveBuild(root, args);
|
|
15
15
|
const raw = rest.find((a) => !a.startsWith('--'));
|
|
16
|
+
// A step range like `1-3` is a `/pb-build` skill affordance (auto-approve
|
|
17
|
+
// through the range, then pause), not a CLI capability — the CLI records one
|
|
18
|
+
// in-flight step at a time. Name it rather than bounce off the generic usage.
|
|
19
|
+
if (raw !== undefined && /^\d+-\d*$/.test(raw)) {
|
|
20
|
+
process.stderr.write(`plumbbob: build takes one step number; \`${raw}\` step ranges are a \`/pb-build\` feature (auto-approve through the range, then pause). Try \`plumbbob build ${raw.split('-')[0]}\`.\n`);
|
|
21
|
+
return 1;
|
|
22
|
+
}
|
|
16
23
|
if (raw === undefined || !/^\d+$/.test(raw) || Number(raw) < 1) {
|
|
17
24
|
process.stderr.write('plumbbob: build needs a step number. Try: plumbbob build 2.\n');
|
|
18
25
|
return 1;
|
package/package.json
CHANGED
package/skills/pb-build/SKILL.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: pb-build
|
|
3
|
-
description: The default engine — read the next planned step from intent, implement it (its done-when, seam, Decisions, Constraints), then verify it through to the approval pause. Swappable — build by hand/vibed/another harness and run /pb-verify instead. `--auto` self-approves and chains to done.
|
|
4
|
-
argument-hint: "[step-number] [--auto]"
|
|
3
|
+
description: The default engine — read the next planned step from intent, implement it (its done-when, seam, Decisions, Constraints), then verify it through to the approval pause. Swappable — build by hand/vibed/another harness and run /pb-verify instead. `--auto` self-approves and chains to done; a step range like `1-3` self-approves through step 3, then pauses.
|
|
4
|
+
argument-hint: "[step-number | step-range] [--auto]"
|
|
5
5
|
disable-model-invocation: true
|
|
6
6
|
model: opus
|
|
7
7
|
allowed-tools: Read, Edit, Write, Bash(plumbbob status:*), Bash(plumbbob build:*), Bash(plumbbob check:*), Bash(plumbbob checkpoint:*), Bash(plumbbob agent:*), Bash(git diff:*)
|
|
@@ -23,9 +23,11 @@ at the pause for your approval. **Re-firing `/pb-build` is itself the clock tick
|
|
|
23
23
|
|
|
24
24
|
## What this skill does, in order
|
|
25
25
|
|
|
26
|
-
1. **Pick the step.** Use the number you were invoked with (e.g. `/pb-build 4`),
|
|
27
|
-
|
|
28
|
-
|
|
26
|
+
1. **Pick the step.** Use the number you were invoked with (e.g. `/pb-build 4`) — or,
|
|
27
|
+
if you were given a range like `/pb-build 1-3`, start at the first number and treat
|
|
28
|
+
the second as the auto-approve ceiling (see the range note under `--auto`). With no
|
|
29
|
+
argument, take the next undone, planned step in `.plumbbob/intent.md`. If there is no
|
|
30
|
+
planned step to build, stop and tell the human to `/pb-step` first.
|
|
29
31
|
2. **Enter the step.** Run `plumbbob build <n>` (records the in-flight STEP +
|
|
30
32
|
SEAM so `/pb-status` shows the step in flight; the seam is awareness, not a
|
|
31
33
|
lock).
|
|
@@ -92,11 +94,34 @@ and approves in the human's place**, and it **chains**:
|
|
|
92
94
|
- **Stop and hand back to the human** the moment any of these is true: the check is red,
|
|
93
95
|
the self-review finds a mismatch (surface exactly what, and do not checkpoint it), a
|
|
94
96
|
bound agent returns `blocked` or `drift` (unblock-and-re-run, or `/pb-refine` — an
|
|
95
|
-
agent cannot advance the loop, C6), a new decision is needed,
|
|
96
|
-
remain.
|
|
97
|
+
agent cannot advance the loop, C6), a new decision is needed, no planned steps
|
|
98
|
+
remain, or the top of a requested range is reached.
|
|
97
99
|
|
|
98
|
-
`--auto`
|
|
99
|
-
human asked for it by name
|
|
100
|
+
`--auto` and a step range are the only paths that checkpoint without a human pause, and
|
|
101
|
+
only because the human asked for it by name; a range re-imposes the pause at its top.
|
|
102
|
+
The default — no flag, no range — always ends at the pause.
|
|
103
|
+
|
|
104
|
+
### A step range (`N-M`) is a bounded `--auto`
|
|
105
|
+
|
|
106
|
+
`/pb-build 1-3` self-approves steps 1 through 3 exactly as `--auto` does, then **pauses
|
|
107
|
+
after step 3** instead of chaining to done. The range *is* the opt-in — you do not also
|
|
108
|
+
pass `--auto`. Run it as the `--auto` loop with one extra halt: **stop before building
|
|
109
|
+
any next step whose plan number is past the top of the range.** It adds no machinery —
|
|
110
|
+
just the one more entry already in the halt list above.
|
|
111
|
+
|
|
112
|
+
- **`N-M` with N ≤ M** — build N…M, self-approving and checkpointing each, then pause at
|
|
113
|
+
M. `N-N` is just the single step `N` (which already ends at the pause).
|
|
114
|
+
- **N > M** (e.g. `3-1`) — that is not a range you can walk; report it and stop rather
|
|
115
|
+
than guess the intent.
|
|
116
|
+
- **M past the last planned step** (e.g. `1-9` with three steps) — build through the
|
|
117
|
+
last planned step and stop; that is the existing "no planned steps remain" halt, not
|
|
118
|
+
an error.
|
|
119
|
+
- **A step inside the range won't build** (missing, or its seam won't parse) — `plumbbob
|
|
120
|
+
build <n>` fails exactly as it always does; surface it and stop, the same as a red
|
|
121
|
+
check. Do not skip past the gap.
|
|
122
|
+
- **N is above the next undone step** — you are jumping over earlier planned work; note
|
|
123
|
+
that you are skipping the steps before N, then proceed (the same latitude as a
|
|
124
|
+
single-number jump like `/pb-build 4`).
|
|
100
125
|
|
|
101
126
|
## The hard contracts
|
|
102
127
|
|
|
@@ -105,8 +130,9 @@ human asked for it by name. The default — no flag — always ends at the pause
|
|
|
105
130
|
- **Build the decided step, not a new one.** Implement what `intent.md` settled. A
|
|
106
131
|
new idea mid-build is a `/pb-park`, not an edit.
|
|
107
132
|
- **Default ends at the pause.** Implement → verify → wait for approval; never
|
|
108
|
-
checkpoint without it. Only an explicit `--auto` lets the agent approve
|
|
109
|
-
and it still halts on a red check or any mismatch
|
|
133
|
+
checkpoint without it. Only an explicit `--auto` or a step range lets the agent approve
|
|
134
|
+
in your place, and it still halts on a red check or any mismatch — a range also stops
|
|
135
|
+
at its top.
|
|
110
136
|
- **Agents feed the beat; they never advance it** (C6/D45). `before` loads context,
|
|
111
137
|
`build` writes the diff, `after` is advisory — none can checkpoint, flip a step, or
|
|
112
138
|
chain. `blocked` → unblock and re-run; `drift` → `/pb-refine`. You are still the one
|