scriptoriumadmin/smriti
1
0
Fork 0
mirror of https://github.com/himanshudongre/smriti.git synced 2026-10-09 03:17:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Sync README and CONTRIBUTING after V1 worktree merge

Browse source 
- README: 17 → 21 MCP tools, add worktrees bullet to coordination
  primitives (notes V1 = CRUD primitive only; binding + state-brief
  enrichment deferred to V2)
- CONTRIBUTING: 17 → 21 MCP tools

DECISIONS.md and skill pack template are intentionally not touched —
the V1 prompt explicitly deferred those to V2 so the rationale and
skill pack reflexes can be written together with the actual usage
patterns we'll learn from V2 (claim binding + state brief).
This commit is contained in:
Himanshu Dongre 2026-05-04 01:10:02 +05:30
parent b5ccdce758
commit 571bbbcc3e
2 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
CONTRIBUTING.md
View file

@ -133,7 +133,7 @@ EXPECTED_OUTCOMES at minimum.
Smriti has three agent-facing surfaces beyond the chat UI:
- **CLI** (`cli/smriti_cli/main.py`) — `smriti` command, 8 subcommand groups
- **MCP server** (`cli/smriti_cli/mcp_server.py`) — `smriti-mcp` command, 17 tools
- **MCP server** (`cli/smriti_cli/mcp_server.py`) — `smriti-mcp` command, 21 tools
- **Skill pack** (`cli/smriti_cli/skill_pack/`) — versioned instruction files for Claude Code and Codex
Changes to any of these should include corresponding test coverage in `cli/tests/`.

3
README.md
View file

@ -30,7 +30,7 @@ The strongest proof: two agents started near-simultaneously, read the same task
### Four surfaces on the same core
1. **A CLI** (`smriti`) — how a coding agent reads and writes reasoning state from a shell tool loop.
2. **An MCP server** (`smriti-mcp`) — the same surface wrapped as 17 MCP tools for Claude Code, Cursor, and Windsurf.
2. **An MCP server** (`smriti-mcp`) — the same surface wrapped as 21 MCP tools for Claude Code, Cursor, and Windsurf.
3. **An agent skill pack** — a versioned instruction file (`.claude/skills/smriti/SKILL.md` or `AGENTS.md`) that teaches the agent when to checkpoint, when not to, how to detect drift, and how to select complementary work. Install once per project.
4. **A chat UI** — how a human reads, steers, and debugs the shared state. Dashboard with checkpoint timeline, active claims, milestone markers, and needs-attention signals.
@ -57,6 +57,7 @@ One project, one Smriti Space, multiple agents. Each reads the state, declares i
- **Backend capabilities** (`/health`) — the backend advertises its feature surface so agents can detect stale backends.
- **Compact mode** (`--compact`) — artifact content omitted for token efficiency; labels and recovery instructions preserved.
- **Project metrics** (`smriti metrics <space>`) — coordination, state quality, and branch lifecycle KPIs computed on demand from existing data.
- **Worktrees** (`smriti worktree open/list/show/close`) — first-class git worktree primitive so multiple agents can work on the same project without sharing one checkout. Each agent gets its own working tree and staging index, eliminating the cross-agent commit pollution failure mode that motivated the feature. (V1: CRUD primitive only. Claim ↔ worktree binding and state-brief enrichment land in V2.)
---