Skills › gstack › setup-gbrain › claude-md-persist.md

claude-md-persist.md

40 lines · setup-gbrain/sections/claude-md-persist.md at 3f79d81

Project instruction file Names a skill Uses an outside tool

Most marks come from matching words in the file, so treat them as pointers.

1

2

3Find-and-replace (or append) the section. Block format depends on mode:

Find-and-replace (or append) the section. Block format depends on mode:

Raw lines 1 to 4

5### Path 4 (Remote MCP)

7```markdown

8## GBrain Configuration (configured by /setup-gbrain)

9- Mode: remote-http

10- MCP URL: {MCP_URL}

11- Server version: gbrain v{SERVER_VERSION} (from Step 4c verify)

12- Setup date: {today}

13- MCP registered: yes (user scope)

14- Token: stored in ~/.claude.json (do not commit; never written to CLAUDE.md)

15- Artifacts repo: {gstack_artifacts_remote URL or "none"}

16- Artifacts sync: {off|artifacts-only|full}

17- Current repo policy: {read-write|read-only|deny|unset}

18```

20The bearer token is **never** written to CLAUDE.md (CLAUDE.md is checked

21in to git in many projects). It lives only in `~/.claude.json` where

22`claude mcp add` placed it.

Path 4 (Remote MCP)

## GBrain Configuration (configured by /setup-gbrain)
- Mode: remote-http
- MCP URL: {MCP_URL}
- Server version: gbrain v{SERVER_VERSION}  (from Step 4c verify)
- Setup date: {today}
- MCP registered: yes (user scope)
- Token: stored in ~/.claude.json (do not commit; never written to CLAUDE.md)
- Artifacts repo: {gstack_artifacts_remote URL or "none"}
- Artifacts sync: {off|artifacts-only|full}
- Current repo policy: {read-write|read-only|deny|unset}

The bearer token is never written to CLAUDE.md (CLAUDE.md is checked in to git in many projects). It lives only in ~/.claude.json where claude mcp add placed it.

Raw lines 5 to 23

Uses an outside tool MCP :5

Project instruction file CLAUDE.md :14

24### Paths 1, 2a, 2b, 3 (Local stdio)

26```markdown

27## GBrain Configuration (configured by /setup-gbrain)

28- Mode: local-stdio

29- Engine: {pglite|postgres}

30- Config file: ~/.gbrain/config.json (mode 0600)

31- Setup date: {today}

32- MCP registered: {yes/no}

33- Artifacts sync: {off|artifacts-only|full}

34- Current repo policy: {read-write|read-only|deny|unset}

35```

37Do not write a `## GBrain Search Guidance` block here. `/sync-gbrain` is its

38only writer: it writes the block after its read check confirms this repo's

39code index answers, and replaces any older block under the same heading.

40Step 10 offers to run `/sync-gbrain`.

Paths 1, 2a, 2b, 3 (Local stdio)

## GBrain Configuration (configured by /setup-gbrain)
- Mode: local-stdio
- Engine: {pglite|postgres}
- Config file: ~/.gbrain/config.json (mode 0600)
- Setup date: {today}
- MCP registered: {yes/no}
- Artifacts sync: {off|artifacts-only|full}
- Current repo policy: {read-write|read-only|deny|unset}

Do not write a ## GBrain Search Guidance block here. /sync-gbrain is its only writer: it writes the block after its read check confirms this repo's code index answers, and replaces any older block under the same heading. Step 10 offers to run /sync-gbrain.

Raw lines 24 to 40

Uses an outside tool MCP :32

Names a skill sync-gbrain :37