@lacodda/rigger 0.20.0 → 0.21.0

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.
Files changed (2) hide show
  1. package/README.md +40 -22
  2. package/package.json +2 -2
package/README.md CHANGED
@@ -77,11 +77,37 @@ $ rigger open sample
77
77
  Starting claude in C:\dev\sample with the packet for sample
78
78
  ```
79
79
 
80
- Connect the MCP server instead, and the assistant reads the same packet and writes back to the record as it works - decisions, findings and pitfalls become events, not lines in a transcript nobody opens again:
80
+ The MCP server is how the assistant reads that packet and writes back to the record as it works - decisions, findings and pitfalls become events, not lines in a transcript nobody opens again. The installer registers it, along with the hook that closes a sitting when the assistant stops:
81
81
 
82
82
  ```console
83
- $ claude mcp add rigger -- rigger mcp
84
- Added stdio MCP server rigger with command: rigger mcp to local config
83
+ $ irm https://raw.githubusercontent.com/lacodda/rigger/main/tools/install.ps1 | iex
84
+ ...
85
+ Registered the rigger MCP server with claude.
86
+ Added the Stop hook: a sitting now closes itself.
87
+ ```
88
+
89
+ And for you, rather than for the assistant, the project's own screen - what it is, where it stands, what it has written down:
90
+
91
+ ```console
92
+ $ rigger show sample
93
+ sample
94
+ A sample product
95
+
96
+ path C:\dev\sample
97
+ gate cargo fmt --all --check && cargo clippy --all-targets -- -D warnings && cargo test
98
+
99
+ Last shipped v0.2.0 on 2026-09-03, 2 commits since
100
+ 1 versions planned, 2 tasks open
101
+
102
+ Current stage: v0.3.0 · Search
103
+ > full-text index
104
+ a query language
105
+
106
+ Written down:
107
+ vision Vision of sample 2026-09-12 rigger doc show sample vision
108
+
109
+ Next step
110
+ Ship the importer next.
85
111
  ```
86
112
 
87
113
  What actually shipped is not taken on trust. `sync` reads the repository's tags and commits in-process and writes what they prove; where the plan says a version shipped and no tag agrees, the disagreement is reported rather than corrected:
@@ -141,32 +167,24 @@ sample v0.2.0 — aimed at 2026-W37, 2 weeks late
141
167
 
142
168
  A project is named after its directory - the name you call it by, not the one its manifest publishes under - and `--name` overrides. Every command that shows facts also prints them with `--json`.
143
169
 
144
- ## What it will do
170
+ ## What you get
145
171
 
146
- - **Projects, versions, tasks, sessions.** A project has a map of versions; a version is a stage that ends in a tag; a task is a unit of work inside a version (at home) or a ticket across several projects and branches (at work). One model, two profiles.
172
+ - **Projects, versions, tasks, sessions.** A project has a map of versions; a version is a stage that ends in a tag; a task is a unit of work inside a version (at home) or a ticket across several projects and branches (at work).
147
173
  - **Facts from git.** A pushed tag means the version shipped, on that date. Commits since the last tag are activity. The plan cannot claim more than git confirms.
148
- - **A context packet instead of a hub.** `rigger context <project>` prints what the assistant needs to start - state, current stage, open questions, last events, next step - within a fixed token budget.
149
174
  - **An MCP server as the assistant's only pen.** Decisions, findings, pitfalls, changes and the next step are recorded as events through tools, not by editing markdown.
150
- - **The owner's inbox.** Every question waiting for your answer, across all projects, in one list.
151
- - **A release calendar** with tiers and rhythm, derived from the same data - the plan is a week, the fact is a tag, and the gap between them is named.
175
+ - **The owner's inbox and a release calendar**, both derived from the same record rather than kept by hand.
152
176
  - **Hubs as an export.** The markdown files you keep in Obsidian are generated from the database, not written by hand.
153
- - **Thin project skills.** The file an assistant reads first is one template filled from the record, not sixteen kilobytes of ritual kept by hand per project.
177
+ - **Thin project skills.** The file an assistant reads first is one template filled from the record.
154
178
 
155
179
  ## Status
156
180
 
157
- v0.20.0 puts the rules of the work into the record and makes the gate something the record witnessed. The rituals of a line and the ones a project states about itself were pasted into every project skill - seventeen copies of nearly the same text, about 390 KB read before every session, and a change to them was seventeen edits or, more often, one edit and sixteen skills quietly out of date. They are documents now: the line's hang off a project named after the profile, a project's off the project, and `rigger rules [<project>]` prints both. The skill that reads them is 1.3 KB and says three things - `context`, `rules`, `session end`. A project states its gate once (`rigger project set <project> --gate "..."`), the packet prints it on one line, and `rigger gate <project>` runs it: every run is kept with its verdict and how long it took, red exits non-zero so a hook can act on it, and `session end` names a gate this sitting left red. `import --answers <file>` reads the questionnaire an owner fills in before a plan is reworked - a fork becomes a decision naming the option taken **and the ones it beat**, an idea ticked becomes a wish, one left unticked a decision - so the page stops being the only place those choices live. The wishes file is read in once and then watched: `doctor` says when something has been left in it, since nothing reads it at every session any more. Found on the way, and fixed: a generated hub read back struck versions the export had simply scrolled past, and a hub directory that was not there was read as an empty one - each of which told the record to strike every stage of a project while exiting zero. Before it, v0.19.0 moves a project's handwritten texts into the record. The vision, the rituals a project states about itself, the preamble of its decisions journal and every research note used to live only as files in a hub - the reason a hub had to exist at all - and `rigger doc list|show|add|edit|remove` now keeps them where everything else is kept. `import` takes them in, `export --docs` writes them back out as an optional cache, and over MCP `doc_show` and `doc_write` let an assistant write a research note or correct a vision into the record rather than into a file somebody has to remember to import. Editing goes through `$EDITOR` - scheda when it is installed, since it takes the `--wait` an editor has to - and a new document starts from the questions its kind exists to answer, from a skeleton `doc template --write` makes yours. The record being one file made its insurance the first thing to build: `backup --keep` rotates the copies, `doctor` says how old the newest is, and `session end` takes one when the newest predates today. `export --check` now shows the lines that would change rather than only the names of the files, because the question it answers is whether something written by hand is about to be thrown away. Before it, v0.18.0 brought the desk its cards. A card is a ticket in the record - a key, the aliases it went by before it moved, a summary, the repositories it is worked in with a branch in each, and everything written against it. `rigger task find` takes a task exactly as it was handed over - an id, a title, two case numbers - and says whether to take a card, ask, or make a new one, with the matching a script ran a desk on for a year: an id is certain, a title is compared by bigrams and by the words it shares, a case number lifts a card, and a number mentioned only in what was written against another card is the trail of a task that moved. `task new`, `open`, `active`, `close`, `link`, `rename`, `note` and `context` are the card's day; over MCP, `task_find`, `task_context` and a `task` argument on every recording tool. Before it, v0.17.0 gave rigger a second way of working. A profile is a record of its own - its database, its roots, its way of naming work - and every command reads the current one without being told: `line` for the products of a line, `tickets` for the desk at work, where the unit is an id worked on branches across several repositories. The config is a TOML file a person edits; `profile add`, `set` and `use` write it. The database from before profiles is moved into the default profile on first use, with the old file kept. A task's status is a word from a vocabulary now - new, active, waiting-handoff, frozen, done - given by `task status` or `set_task_status` over MCP and shown in the packet; a hub's empty box means "not done" and no longer resets it. This is the release that changes the shape of the data before 1.0; the schema migrates itself, with a copy of the database taken first. Before it, v0.16.0 put a whole line through rigger. Every hub of a real line is now written from the record and every project skill is generated, and what that took was the other half of reading a hub: a hub kept by hand for a month is not the hub the first import read. A task struck from the plan is dropped rather than kept as open work for ever, a stage renumbered by hand leaves no ghost, a question the owner struck is withdrawn, a version known only from a tag is a fact rather than an empty changelog entry, and a diary entry read once without its date is one entry. A hub the record writes keeps growing without a hand: `session end` leaves its diary entry in the record, and `note --kind state` (`record_state` over MCP) puts a line at the top of the README's state block. `doctor --hubs` names the hubs still kept by hand. Before it, v0.15.0 made moving a project onto rigger two commands. `rigger adopt <dir> --hubs <dir>` walks a directory of checkouts, records each one that has a hub, imports the hub and reads the tags - the three commands a project used to take, once for a whole line, and the command to run again when the line has grown. `rigger skill <project> --install` writes the project's skill from one template and the record, so a change to the ritual is one edit rather than seventeen; a line writes its own template, a project keeps what only it can say in a file of its hub, and a skill somebody wrote by hand is not replaced until asked. Found on the way: a second import of a hub put the hub's release date back over the one the tag proved, and every sync after it reported the version shipped anew - a fact from git now stays. Before it, v0.14.0 turned the record back into notes: `rigger export` writes a project's hub out of the database and `import` reads it back, nineteen of the twenty hubs of a real line byte for byte, and a hub kept by hand is not overwritten until `--adopt` hands it over. Before that: the database, `import`, the context packet, the `mcp` server, facts from git, a chronicle that writes itself, search, the owner's inbox and digest, the release calendar, the week as a brief and a shopfront queue, the cycle looked back on, and sittings the record knows. The road to 1.0 is twenty-two small releases in seven blocks:
158
-
159
- | Block | Versions | What it delivers |
160
- | --- | --- | --- |
161
- | Record | 0.1 - 0.5 | database and projects, hub import, the context packet, a Claude Code session from it, the MCP server |
162
- | Facts | 0.6 - 0.8 | tags and commits as truth, changes read from commits, search and "why" |
163
- | Owner | 0.9 - 0.12 | inbox and digest, the release calendar, the Monday brief, retro |
164
- | Sessions | 0.13 - 0.14 | sessions with an end-of-session journal, hubs exported from the database |
165
- | Line | 0.15 - 0.16 | thin project skills, every project of a line recorded at once |
166
- | Tasks | 0.17 - 0.21 | the ticket profile, task cards, activity from branches, incoming material, snooze and handoff |
167
- | Stabilisation | 0.22 | `--json` everywhere, docs, a signed binary where needed |
181
+ The record, the context packet, the MCP server, facts from git, the owner's
182
+ inbox, the release calendar and thin project skills are in daily use across
183
+ the whole line. The rules a line and a project state about themselves, and
184
+ the gate a project runs, are documents in the record rather than pasted into
185
+ every project's skill.
168
186
 
169
- **1.0 "Truth in the database":** a full week where every session on every project runs through rigger and no hub is edited by hand. A desktop window (Tauri) and code knowledge follow in 1.x.
187
+ Released versions and what landed in each: [CHANGELOG](https://github.com/lacodda/rigger/blob/main/CHANGELOG.md).
170
188
 
171
189
  ## Install
172
190
 
@@ -191,4 +209,4 @@ https://lacodda.github.io/rigger/ - getting started, concepts, and a reference p
191
209
 
192
210
  ## License
193
211
 
194
- MIT - see https://github.com/lacodda/rigger/blob/main/LICENSE.
212
+ MIT (c) [Kirill Lakhtachev](https://lacodda.com)
package/package.json CHANGED
@@ -1,8 +1,8 @@
1
1
  {
2
2
  "name": "@lacodda/rigger",
3
- "version": "0.20.0",
3
+ "version": "0.21.0",
4
4
  "rigger": {
5
- "binary": "v0.20.0"
5
+ "binary": "v0.21.0"
6
6
  },
7
7
  "description": "One seat for all your projects and tasks: a local record of what is done, what is next and when it ships - read by you and your coding assistant",
8
8
  "license": "MIT",