tokenjam 0.6.3 → 0.6.5

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 +11 -5
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -19,7 +19,11 @@ npx tokenjam onboard # or: pipx install tokenjam && tj onboard
19
19
 
20
20
  ## What you get
21
21
 
22
- `tj onboard` is guided setup: it writes a config, generates an ingest secret, and asks how you use AI agents (Claude Code, Codex, or your own SDK/API agents) to wire the right path. For Claude Code and Codex that means backfilling recent history and installing a statusline and hooks for live capture; restart and you're live. Onboarding unlocks all six analyzers, the Lens dashboard, and the zero-token statusline in one command.
22
+ `tj onboard` is guided setup: it writes a config, generates an ingest secret, and asks how you use AI agents (Claude Code, Codex, or your own SDK/API agents) to wire the right path. For Claude Code and Codex that means backfilling recent history and installing a statusline and hooks for live capture; restart and you're live. Onboarding unlocks the analyzer suite, the Lens dashboard, and the zero-token statusline in one command.
23
+
24
+ Your answer also decides **which analyzers run**. A coding-agent user (Claude Code, Codex) and an SDK/API user can change different things: the coding agent's harness builds the request and owns the prompt template, while an SDK process has no on-disk transcript and no subagent dispatch. Most analyzers run for both; the ones whose fix your persona can't reach are skipped rather than shown as advice you can't act on.
25
+
26
+ And it doesn't stop at advice. Every analyzer ends in a fix you can apply: a rule written into the right instruction file, an unused MCP server scoped down, a subagent pinned to a cheaper model, a cache breakpoint placed in the request your code builds. Each one is staged as a diff, dry-run by default, and undoable.
23
27
 
24
28
  ## Commands
25
29
 
@@ -29,7 +33,8 @@ All arguments pass straight through to the Python CLI, so any `tj` subcommand an
29
33
  |---|---|
30
34
  | `npx tokenjam onboard` | Guided setup: writes a config, generates an ingest secret, and optionally installs the background daemon for live capture. |
31
35
  | `npx tokenjam context` | Where your quota goes: re-read vs. net-new share, recurring inclusions, `/compact` candidates. |
32
- | `npx tokenjam optimize` | Cost-saving candidates: model downsizing, cache opportunities, prompt trimming, workflow reuse, subagent right-sizing. |
36
+ | `npx tokenjam optimize` | Cost-saving candidates from your actual usage: recurring blockers, repeat context, model downsizing, subagent right-sizing, unused MCP servers, oversized instruction files, and more. |
37
+ | `npx tokenjam rules list` | The fixes on offer, and the files each would be written into. `stage` / `check` / `apply` / `undo` complete the loop. |
33
38
  | `npx tokenjam` | Bare run: still works, still zero-install, still a reference passthrough to the Python CLI. |
34
39
 
35
40
  ## Go deeper
@@ -37,11 +42,12 @@ All arguments pass straight through to the Python CLI, so any `tj` subcommand an
37
42
  `tj onboard` sets up live capture, the local Lens dashboard, and the zero-token statusline in one command. From there:
38
43
 
39
44
  ```bash
40
- tj optimize # cost-saving candidates from your actual usage
41
- tj serve # open the Lens dashboard at http://127.0.0.1:7391/
45
+ tj optimize # cost-saving candidates from your actual usage
46
+ tj rules list # the fixes on offer, and the files they'd be written into
47
+ tj serve # open the Lens dashboard at http://127.0.0.1:7391/
42
48
  ```
43
49
 
44
- - Full feature set, six analyzers, and Lens screenshots: [github.com/Metabuilder-Labs/tokenjam](https://github.com/Metabuilder-Labs/tokenjam)
50
+ - Full feature set, the per-persona analyzer table, and Lens screenshots: [github.com/Metabuilder-Labs/tokenjam](https://github.com/Metabuilder-Labs/tokenjam)
45
51
  - Product site and docs: [tokenjam.dev](https://tokenjam.dev)
46
52
 
47
53
  ## How the launcher works
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "tokenjam",
3
- "version": "0.6.3",
3
+ "version": "0.6.5",
4
4
  "description": "Zero-install launcher for TokenJam (tj): npx tokenjam runs the Python CLI via uvx/pipx and reports the recurring mistakes your AI agent keeps repeating, no setup required.",
5
5
  "keywords": [
6
6
  "claude-code",