Skip to content

Commit 07b14b0

Browse files
Sync Boatstack from Intelligence Flow Labs @ 7faf0ffbc012 (#50)
Co-authored-by: operator-stack-publisher[bot] <operator-stack-publisher[bot]@users.noreply.github.com>
1 parent 6863b2b commit 07b14b0

9 files changed

Lines changed: 65 additions & 41 deletions

CONTRIBUTING.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22

33
# Contributing
44

5-
Boatstack is a generated content distribution. Propose changes to workflow semantics, templates, evidence rules, or generated presentation in [Intelligence Flow](https://github.com/operatorstack/intelligence-flow/tree/004b6c1288661bbbfdcfe96c068f35e48f4c8bb3/labs/12-product-engineering-loop).
5+
Boatstack is a generated content distribution. Propose changes to workflow semantics, templates, evidence rules, or generated presentation in [Intelligence Flow](https://github.com/operatorstack/intelligence-flow/tree/7faf0ffbc012b9830eb7c23c8b845ebba4be6da1/labs/12-product-engineering-loop).
66

77
The Boatstack repository receives product/runtime changes through a generated pull request. Review the PR's `UPSTREAM.json`, tests, adapter diff, and context-size change; do not hand-edit generated output on `main`. `.github/workflows` is the exception: it is Boatstack's executable control plane, excluded from scheduled projection and changed only through a separate manually reviewed Boatstack PR.
88

README.md

Lines changed: 15 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@
1010

1111
## A delivery harness for AI coding agents
1212

13-
<!-- boatstack-claim:portable-product-flow -->Boatstack connects the work from an idea to a reviewed PR. Keep using Cursor, Codex, or Claude Code, with the models and specialist skills that fit the work. Boatstack keeps the plan, decisions, gaps, tests, review findings, and project context connected along the way.
13+
<!-- boatstack-claim:portable-product-flow -->Boatstack connects the work from an idea to a reviewed PR. Keep using Cursor, Codex, Claude Code, or Gemini CLI, with the models and specialist skills that fit the work. Boatstack keeps the plan, decisions, gaps, tests, review findings, and project context connected along the way.
1414

1515
The agent remains free to build. Before it says the work is done, Boatstack asks for the approval, tests, review, and recorded evidence appropriate to the change.
1616

@@ -22,17 +22,17 @@ The agent remains free to build. Before it says the work is done, Boatstack asks
2222

2323
| You change | Boatstack keeps |
2424
|---|---|
25-
| Cursor, Codex, or Claude Code | The same path from planning through PR preparation |
25+
| Cursor, Codex, Claude Code, or Gemini CLI | The same path from planning through PR preparation |
2626
| Lower-cost, general, or frontier model | The same approval, testing, and review requirements |
2727
| React guidance, gstack, Spec Kit, or another skill | Human approval and evidence remain authoritative |
2828
| Session, worktree, or feature | Durable decisions, gaps, evidence, and code state in the repository |
2929

3030
## Install with your coding agent
3131

32-
Copy this into Cursor, Codex, or Claude Code while the repository is open:
32+
Copy this into Cursor, Codex, Claude Code, or Gemini CLI while the repository is open:
3333

3434
```text
35-
Install Boatstack in this repository from https://github.com/operatorstack/boatstack. Detect whether you are running in Cursor, Codex, or Claude Code; create or use a chore/install-boatstack branch; run the official installer for this operating system; default to core unless I request gstack or Spec Kit; keep all portable host adapters; run Boatstack doctor; show me the generated files and installation diff; and prepare the installation PR without merging it or starting product work.
35+
Install Boatstack in this repository from https://github.com/operatorstack/boatstack. Detect whether you are running in Cursor, Codex, Claude Code, or Gemini CLI; create or use a chore/install-boatstack branch; run the official installer for this operating system; default to core unless I request gstack or Spec Kit; keep all portable host adapters; run Boatstack doctor; show me the generated files and installation diff; and prepare the installation PR without merging it or starting product work.
3636
```
3737

3838
Install Boatstack in its own infrastructure PR and merge it before starting a feature. Install once per Git clone; linked worktrees reuse the verified runtime and restore their ignored local helper automatically.
@@ -46,15 +46,16 @@ Install Boatstack in its own infrastructure PR and merge it before starting a fe
4646
|---|---|
4747
| Claude Code | `/auto-plan` |
4848
| Cursor | `/auto-plan` |
49+
| Gemini CLI | `/auto-plan` |
4950
| Codex | `$boatstack auto-plan` |
5051

5152
That is all you need to learn up front. Boatstack shows one next action at a time through approval, building, tests, review, and PR preparation.
5253

53-
When you return after an interruption, run `/boatstack-next` in Claude Code or Cursor, or `$boatstack next` in Codex. Boatstack reports the repository-verified stage and one next action without changing state. It distinguishes a feature that has not started from one that is complete.
54+
When you return after an interruption, run `/boatstack-next` in Claude Code, Cursor, or Gemini CLI, or `$boatstack next` in Codex. Boatstack reports the repository-verified stage and one next action without changing state. It distinguishes a feature that has not started from one that is complete.
5455

55-
`$boatstack run` in Codex or `/boatstack-run` in Claude Code and Cursor starts from one saved plan and continues through publication, pausing for approvals and product decisions. It checks branch freshness before delivery; it never merges or deploys.
56+
`$boatstack run` in Codex or `/boatstack-run` in Claude Code, Cursor, and Gemini CLI starts from one saved plan and continues through publication, pausing for approvals and product decisions. It checks branch freshness before delivery; it never merges or deploys.
5657

57-
In Claude Code and Cursor, that guidance moves through `/plan-gate``/build``/test-gate``/review-gate``/ship-gate`. In Codex, use the same operation names after `$boatstack`.
58+
In Claude Code, Cursor, and Gemini CLI, that guidance moves through `/plan-gate``/build``/test-gate``/review-gate``/ship-gate`. In Codex, use the same operation names after `$boatstack`.
5859

5960
> The diagram shows what Boatstack guides—not a checklist you need to memorize.
6061
@@ -66,7 +67,7 @@ In Claude Code and Cursor, that guidance moves through `/plan-gate` → `/build`
6667

6768
After Build, describe changes normally. Boatstack records them, preserves valid work, and resumes at the earliest boundary.
6869

69-
Invoke `/repair` in Claude Code or Cursor, or `$boatstack repair` in Codex. It needs an active delivery and the exact change; earlier work routes to planning or Build.
70+
Invoke `/repair` in Claude Code, Cursor, or Gemini CLI, or `$boatstack repair` in Codex. It needs an active delivery and the exact change; earlier work routes to planning or Build.
7071

7172
```text
7273
“This is wrong” → record → repair → test → review
@@ -107,7 +108,7 @@ Enabled repositories require a categorized `CHANGELOG.md` → `Unreleased` entry
107108

108109
| Part | Its job |
109110
|---|---|
110-
| **Coding agent** — Cursor, Codex, or Claude Code | Executes the work in your repository |
111+
| **Coding agent** — Cursor, Codex, Claude Code, or Gemini CLI | Executes the work in your repository |
111112
| **Model** — lower-cost, general, or frontier | Reasons, writes, and evaluates within the agent |
112113
| **Skill** — React guidance, gstack, Spec Kit, or another specialty | Adds expertise for a particular kind of work |
113114
| **Boatstack** | Carries the delivery path, saved context, and proof of completion across them |
@@ -124,7 +125,7 @@ This does not mean every model performs equally. [See the evidence and paired ev
124125

125126
## Why these steps?
126127

127-
They come from coding failures observed in benchmark and product-repository work—not guesses. Every safeguard links what happened, what Boatstack now does, and whether that behavior has actually been tested.
128+
They derive from coding failures observed in benchmark and product work—not guesses. Each link explains what happened, what Boatstack does, and whether that behavior has actually been tested.
128129

129130
| What happened | What Boatstack does | Current evidence |
130131
|---|---|---|
@@ -139,7 +140,7 @@ They come from coding failures observed in benchmark and product-repository work
139140

140141
## A small example
141142

142-
A request said, “Add a password reset button,” but the product used passwordless sign-in and had no reset route. Boatstack surfaced the conflict instead of building the button literally. The human chose dual authentication; later, review caught an unsafe recovery-session assumption and returned the change for repair before PR preparation.
143+
A request asked to “Add a password reset button,” but the product used passwordless sign-in. Boatstack flagged the conflict. The developer chose dual authentication; later, review caught an unsafe recovery assumption and prompted a repair.
143144

144145
[Follow the sanitized walkthrough](docs/account-recovery-walkthrough.md) or [ship your first feature](docs/getting-started.md).
145146

@@ -170,14 +171,14 @@ The installer previews generated paths, verifies the platform helper, offers opt
170171

171172
## Find what you need
172173

173-
**Start:** [Getting started](docs/getting-started.md) · [Generated files](docs/generated-files.md) · [Troubleshooting](docs/troubleshooting.md)
174+
**Start:** [Getting started](docs/getting-started.md) · [Files](docs/generated-files.md) · [Troubleshooting](docs/troubleshooting.md)
174175

175176
**Inspect:** [Why these steps](docs/why-these-steps.md) · [Validation and evidence](docs/validation-and-evidence.md) · [Safety](docs/safety.md)
176177

177-
**Go deeper:** [Evidence-engineered coding](docs/evidence-engineered-coding.md) · [Research and design](docs/research-and-design.md) · [Contributing](CONTRIBUTING.md)
178+
**Go deeper:** [Coding](docs/evidence-engineered-coding.md) · [Design](docs/research-and-design.md) · [Contributing](CONTRIBUTING.md)
178179

179180
## Project status
180181

181-
Boatstack is an open-source research prototype. Its workflow and enforcement behavior are tested, but the current record does not prove improved product-delivery success. A paired feature-building benchmark—same model, task, and budget with and without Boatstack—is the next evaluation.
182+
Boatstack is an open-source research prototype. Its workflow and enforcement behavior are tested, but the current record does not prove improved delivery success. A paired feature benchmark—same model, task, and budget—is the next evaluation.
182183

183184
Exact Intelligence Flow provenance and generated file hashes are recorded in [`UPSTREAM.json`](UPSTREAM.json).

UPSTREAM.json

Lines changed: 9 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -12,11 +12,11 @@
1212
},
1313
"files": {
1414
".gitignore": "a7079e923a776f14f1bb3a6aa0a11a133a8e1dfb35af020f327623357b7e3957",
15-
"CONTRIBUTING.md": "c26f3f4606810e5db041f21dc48ebcc3020ba5959103cddd7a001af266a9f470",
16-
"README.md": "a840004db57a129ecd361bb0421adfe02065d86751736dd91953c8a8b178e5ef",
17-
"assets/boatstack-journey.svg": "c1f7fe2741f5e9ca66bb3fe9b103e6364ba5acbca8b7a8054768ffd85cf325ea",
15+
"CONTRIBUTING.md": "daad309d104bf02268f3cf89fe0820309ad5f00b470c3c74bf54d199ba72de1e",
16+
"README.md": "590821a4cf3c4b196d3cfb39c972ccbebef7d4d558df817c1f1e88b4fd7ceb07",
17+
"assets/boatstack-journey.svg": "9f016fbfd2881675551a44dafa282cbc7510a7091131005be490c2dbe5e4e051",
1818
"assets/boatstack-mark.svg": "ec96165583b15cfd446c27049d49217973f3e9b1defa5771cc08eec0c9542ce4",
19-
"assets/boatstack-portability.svg": "ce648f5581d16586d25824d3a8132ef1b3d88b73329179173120129d4f74fd24",
19+
"assets/boatstack-portability.svg": "a621b8f4da5159bbfdfd858013ff3fefc3937d7f6e140612a2c82e84283865f9",
2020
"boatstack/SKILL.md": "a63f88eb039c06f34ba018444871b7a0b17c43bdb3ab62f0122732f50345bd6d",
2121
"boatstack/agents/gemini.yaml": "cbf43b387399e456fa6178f86d83e6e35567e6142ff800f8de6ffca306fa963e",
2222
"boatstack/agents/openai.yaml": "68a30a60859556c5a26e16d184594ca243a6043d99c8cf7d66b5dd6d50a93cd1",
@@ -81,10 +81,10 @@
8181
"docs/account-recovery-walkthrough.md": "676034974594a7d1a559b24dbed31d7ccc429eb81404b203ca07bbdaa19ec3d3",
8282
"docs/benchmark-corpus-audit.md": "f2d206fe8579a514f9da82b2c96c19b343ac004be67617e1bd34f0f8e0e5e6c6",
8383
"docs/benchmark-submission-audit.md": "9518abdd17690729c6423f87cab20418ed47b0915b5faa44b9ef975e9e9c3b79",
84-
"docs/evidence-engineered-coding.md": "3f63fc8c92a8f2069368cfbf8f7ac69a0202b05300b2c9ffaa56b70b8154a214",
84+
"docs/evidence-engineered-coding.md": "91c25a6ee6d0553bb2420f2d4c79223e84f3e40b6923378fe227437d4d1e7345",
8585
"docs/generated-files.md": "136422baf0c7fc2bd5100cfe0ebdb3d9d0705dfd7e7d54bf745dd1037e63492c",
8686
"docs/getting-started.md": "eacc814fdffdfa3c7d8052b7cd99a79c04da5c75d88d8b44f3fb68d9afec0316",
87-
"docs/public-claims.json": "44c60c3460165176cfe866d5a695ee7172c92e3192e46e69824d693d549f5d1d",
87+
"docs/public-claims.json": "c79f56cdf2ecf18e5d38e2492b5846fa169ce768842689a870f5252042ebc0f1",
8888
"docs/public-surface.md": "713f7a050b5f339cf948299103ef3800417dccfecf2cc1a4166397ea6f978907",
8989
"docs/research-and-design.md": "d65c66e323037bda5d45aacef5d48afa6bf93da55901378891d235aca3a5684f",
9090
"docs/safety.md": "7b9b5c515d36e683767ec8d3d9d6d119ac93650b2f629d351deadd4c600ed6a6",
@@ -98,7 +98,7 @@
9898
"labs/diagram-json/compiled/evidence.md": "1ba1c989ade070a8ef9a508fbd788d100d7292f2dbacbb2bce895468019f619d",
9999
"labs/diagram-json/compiled/tasks.json": "88f60851abf79d851e9fccc754ff3040034ae595306bc87d64784c19eb403e71",
100100
"labs/diagram-json/compiled/test-matrix.json": "424657ff505768e50fa113801fd8363364a18269d5297480907a993d44063a39",
101-
"labs/diagram-json/plan.lock.json": "a3d49021f016d3bee5c8410f954bf328af2f53ee7288462404d03d2d00f2af10",
101+
"labs/diagram-json/plan.lock.json": "55f1f675530f83307fab542423fc021248abae1601bb1da88aa9814696a0a63c",
102102
"labs/diagram-json/plan.md": "3cc4f533b8d69386deff16b3a594a3ba09d4c0c3db636cccd8c4380084ce6a51",
103103
"labs/diagram-json/questions.md": "74733b015002c8a6777c558e7e997fa48c94850b9bd39054fe9366c97ecf728d",
104104
"labs/diagram-json/request.md": "0808fc41c36779c404f4a3a121167da6e76cac56df526e70f9ed6d3e0d4c02ed",
@@ -131,12 +131,13 @@
131131
"release-notes/2026-07-19-optional-repository-changelog.md": "7ae6bed436c269335ac5055e04438489451bef00836fecb3e5fcb06a18501853",
132132
"release-notes/2026-07-19-valid-skill-frontmatter.md": "a0a002f7891474d7d1eea49e3234cae5ddbd941158726b83555dc48474181a92",
133133
"release-notes/2026-07-20-gemini-cli-integration.md": "d829b4fafb3a02dd766e018558b20bf1bc948dd5e337911d6a7c8b54c83c9942",
134+
"release-notes/2026-07-20-portability-diagram-dark-theme.md": "b06bebec1361b21ef6deb8c8f43168d189803a32588aeb803ea4b441525a77e2",
134135
"release-notes/2026-07-20-speak-software-standards.md": "a8890ed7eb38868bdf3035572d71785ca89abd3ffc3a314a5dc5315150afe397"
135136
},
136137
"generator": "operatorstack/intelligence-flow:boatstack-distribution",
137138
"schema_version": 1,
138139
"source": {
139-
"commit": "004b6c1288661bbbfdcfe96c068f35e48f4c8bb3",
140+
"commit": "7faf0ffbc012b9830eb7c23c8b845ebba4be6da1",
140141
"path": "labs/12-product-engineering-loop",
141142
"repository": "operatorstack/intelligence-flow"
142143
}

assets/boatstack-journey.svg

Lines changed: 9 additions & 1 deletion
Loading

assets/boatstack-portability.svg

Lines changed: 14 additions & 3 deletions
Loading

docs/evidence-engineered-coding.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -146,6 +146,6 @@ Delivery and system improvement also remain separate. A failed task may suggest
146146

147147
## What is evidence-backed
148148

149-
The current moves were derived from the Intelligence Flow benchmark corpus and product-repository studies. The generated source commit is [`004b6c1288661bbbfdcfe96c068f35e48f4c8bb3`](https://github.com/operatorstack/intelligence-flow/tree/004b6c1288661bbbfdcfe96c068f35e48f4c8bb3/labs/12-product-engineering-loop).
149+
The current moves were derived from the Intelligence Flow benchmark corpus and product-repository studies. The generated source commit is [`7faf0ffbc012b9830eb7c23c8b845ebba4be6da1`](https://github.com/operatorstack/intelligence-flow/tree/7faf0ffbc012b9830eb7c23c8b845ebba4be6da1/labs/12-product-engineering-loop).
150150

151151
The evidence supports specific failure mechanisms and guardrails. It does not establish that Boatstack is optimal, that control-theory notation proves software quality, or that one workflow dominates every team. Those are evaluation questions, so the distribution preserves measurements, provenance, gaps, and negative results.

0 commit comments

Comments
 (0)