@jjanczur/tyran 0.1.39 → 0.1.40

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.
@@ -11,7 +11,7 @@
11
11
  {
12
12
  "name": "tyran",
13
13
  "description": "A task conductor for Claude Code: multi-agent orchestration with an enforced evidence contract, repo-specific learning, and update-safe local evolution.",
14
- "version": "0.1.39",
14
+ "version": "0.1.40",
15
15
  "source": "./",
16
16
  "author": {
17
17
  "name": "Jacek Janczura",
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "tyran",
3
- "version": "0.1.39",
3
+ "version": "0.1.40",
4
4
  "description": "A task conductor for Claude Code: multi-agent orchestration with an enforced evidence contract, repo-specific learning, and update-safe local evolution.",
5
5
  "author": {
6
6
  "name": "Jacek Janczura",
package/CHANGELOG.md CHANGED
@@ -1,5 +1,20 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.1.40 — 2026-08-17
4
+
5
+ ### Every session pays for these sentences, so they got shorter
6
+
7
+ Fifteen of the nineteen descriptions — ten skills, five agents — rewritten to
8
+ carry only what routes: what it does, when it fires, the one distinguishing
9
+ mechanism. The justifications live in the bodies, which load only when the
10
+ skill fires. Skill total: **4352 → 3868 of 5000** (measured by the same CI
11
+ guard that enforces the cap); the agent descriptions, which the Agent tool
12
+ loads into every session the same way, shed a similar fraction.
13
+
14
+ Nothing lost its trigger — `prompt-tuning` GAINED one (it was the only
15
+ description with no "use when" clause), and `run`'s now names the kanban it
16
+ drives the team from, which 0.1.39 made true.
17
+
3
18
  ## 0.1.39 — 2026-08-17
4
19
 
5
20
  ### A fifth agent, and the conductor plans from the board it shows you
package/README.md CHANGED
@@ -315,7 +315,7 @@ branch), `tyran:reviewer` (may fix what it finds, but editing forfeits
315
315
  suite on the cheapest tier, reports raw counts, never fixes), `tyran:retro`. A skill is admitted only when something already asks
316
316
  for the protocol by name, and every description is loaded into every session
317
317
  whether the skill fires or not — so the combined length is capped and CI
318
- enforces the cap (4352 of 5000 characters). What each one assumes, when it
318
+ enforces the cap (3868 of 5000 characters). What each one assumes, when it
319
319
  fires and who invokes it, is in
320
320
  [skills and agents](https://jjanczur.github.io/tyran/skills/); the prompts
321
321
  themselves are in [`skills/`](skills/) and [`agents/`](agents/). Behind all of
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: implementer
3
- description: Takes one self-contained story from plan to commit or PR on its own branch, with tests and a self-review. Works only in the directory it was given (a worktree when the team runs in parallel), respects the hardware ceiling and the manifest of shared zones, and reports with raw command output rather than adjectives.
3
+ description: Takes one self-contained story from plan to commit or PR on its own branch, with tests and a self-review. Works only in the directory it was given, respects the hardware ceiling and the manifest of shared zones, and reports with raw command output rather than adjectives.
4
4
  ---
5
5
 
6
6
  You are an implementer. You get ONE story and you carry it to the end.
package/agents/retro.md CHANGED
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: retro
3
- description: After an initiative closes, reads the ledger, the notes and the agents' reports and autonomously improves Tyran itself - the conductor skill, the agent roster, new skills, scripts and repo documentation. Its only product is a better Tyran, never product code. Defends hard against bloat and overfitting, so the default answer is to change nothing.
3
+ description: After an initiative closes, reads the ledger, the notes and the agents' reports and improves Tyran itself - skills, agents, scripts and docs, never product code. Defends hard against bloat and overfitting, so the default answer is to change nothing.
4
4
  ---
5
5
 
6
6
  You are the retrospector. Your ONLY product is a **better Tyran**. You do not
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: reviewer
3
- description: Independent quality control on another agent's work - reads the whole diff, runs its OWN verification rather than trusting the author's report, checks that the claimed optimization is actually in the code, and returns APPROVE, REVISED or CHANGES-REQUESTED with numbered, executable counterexamples. May fix what it finds, which forfeits APPROVE. Never reviews its own code.
3
+ description: Independent quality control on another agent's work - reads the whole diff, runs its OWN verification rather than trusting the author's report, and returns APPROVE, REVISED or CHANGES-REQUESTED with executable counterexamples. May fix what it finds, which forfeits APPROVE. Never reviews its own code.
4
4
  tools: Skill, Read, Grep, Glob, Bash, Edit, WebFetch, WebSearch, mcp__*
5
5
  ---
6
6
 
package/agents/scout.md CHANGED
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: scout
3
- description: Fast, cheap reconnaissance over a repo, its documentation, its data or external sources, changing nothing. Returns short, concrete findings with the file path or URL that proves each one. Used by the conductor at the start of a task and through the research phase of a large initiative.
3
+ description: Fast, cheap reconnaissance over a repo, its documentation, its data or external sources, changing nothing. Returns short, concrete findings with the file path or URL that proves each one. Used at the start of a task and through the research phase of a large initiative.
4
4
  tools: Read, Grep, Glob, Bash, WebFetch, WebSearch, mcp__*
5
5
  ---
6
6
 
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: verifier
3
- description: Mechanical validation on the cheapest tier - runs exactly the commands it is handed, reports exit codes and counts verbatim, compares them against the baseline in the handoff, and never edits, fixes or theorizes. A red suite is its product, not its failure. Spawned by the conductor at merge time, and for the serial re-run of a failure measured while other heavy phases ran.
3
+ description: Mechanical validation on the cheapest tier - runs exactly the commands it is handed, reports exit codes and counts verbatim against the handoff's baseline, and never edits, fixes or theorizes. A red suite is its product, not its failure. Spawned by the conductor at merge time and for the serial re-run of a suspect failure.
4
4
  tools: Read, Grep, Glob, Bash
5
5
  ---
6
6
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@jjanczur/tyran",
3
- "version": "0.1.39",
3
+ "version": "0.1.40",
4
4
  "description": "Command-line scripts for the Tyran task conductor (doctor, journal, schema, and repo tooling) for CI and terminals outside Claude Code. Installing this package does NOT install the Claude Code plugin — add that separately with `/plugin marketplace add jjanczur/tyran` inside Claude Code.",
5
5
  "type": "module",
6
6
  "engines": {
@@ -1,5 +1,5 @@
1
1
  ---
2
- description: Drive a real browser and come back with a MEASUREMENT rather than an impression - deterministic waits instead of sleeps, console errors and >=400 responses as counts, computed styles dumped to JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
2
+ description: Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
3
3
  ---
4
4
 
5
5
  # Browser check — proving a UI works, in numbers
@@ -1,5 +1,5 @@
1
1
  ---
2
- description: The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, test quality, lifecycle) and the rule that a finding is refuted before it is reported. The verdict itself stays with the reviewer agent. Use when reviewing a diff or a pull request.
2
+ description: The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request.
3
3
  ---
4
4
 
5
5
  # Code review — reading depth
@@ -1,5 +1,5 @@
1
1
  ---
2
- description: The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit and again after. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass, before promoting a skill, or when code has grown noisy without growing capable.
2
+ description: The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
3
3
  ---
4
4
 
5
5
  # Deslop — the pass that removes rather than adds
@@ -1,5 +1,5 @@
1
1
  ---
2
- description: Build a UI against a frozen visual reference without drift. An inventory extracted from the reference before any code, a relics list for what exists but should not, and a gate that MEASURES rather than judges - computed styles on a fixture carrying the reference's own data. Use when a mockup, design spec or screenshot is the contract.
2
+ description: Build a UI against a frozen visual reference without drift - an inventory extracted before any code, a relics list, and a gate that MEASURES computed styles on a fixture carrying the reference's own data. Use when a mockup, design spec or screenshot is the contract.
3
3
  ---
4
4
 
5
5
  # Fidelity gate — building against a frozen visual reference
@@ -1,5 +1,5 @@
1
1
  ---
2
- description: Work a reviewer's comments on a pull request to the end. Enumerate all three comment surfaces before triaging any, give every comment a disposition - fixed, declined with a reason, or ticketed - push before you reply, and resolve only what you addressed. Use when a PR comes back with review feedback or a red check.
2
+ description: Work a reviewer's comments on a pull request to the end - all three comment surfaces enumerated before any is triaged, every comment fixed, declined with a reason, or ticketed, push before you reply. Use when a PR comes back with review feedback or a red check.
3
3
  ---
4
4
 
5
5
  # PR feedback — closing the loop with a human reviewer
@@ -1,5 +1,5 @@
1
1
  ---
2
- description: Iterate on a prompt, or on anything whose quality is measured by non-deterministic model output, without chasing noise. A noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording, and detectors that surface candidates rather than defects.
2
+ description: Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.
3
3
  ---
4
4
 
5
5
  # Prompt tuning — working with non-deterministic output
@@ -1,5 +1,5 @@
1
1
  ---
2
- description: Close an initiative by learning from it. Spawns the retrospective agent over the ledger, the notes and the agents reports, records what it changed and what it rejected, and writes durable facts about this repo into .tyran/knowledge/. Runs automatically at the end of an initiative; also available as /tyran:retro.
2
+ description: Close an initiative by learning from it - spawns the retrospective agent over the ledger, the notes and the agents' reports, records what changed and what was rejected, and writes durable repo facts into .tyran/knowledge/. Runs at the end of an initiative; also available as /tyran:retro.
3
3
  ---
4
4
 
5
5
  # Retro
@@ -1,5 +1,5 @@
1
1
  ---
2
- description: Find the mechanism behind a failure instead of patching its symptom. Reproduce first, change one variable per experiment with the prediction written before the run, bisect rather than re-read, and exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
2
+ description: Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
3
3
  ---
4
4
 
5
5
  # Root cause — working a failure down to its mechanism
@@ -1,5 +1,5 @@
1
1
  ---
2
- description: Conduct a task end to end, from a one-line fix to a multi-day programme. Works interactively by default - a short interview, then autonomous execution to the finish. Classifies the task (S/M/L/XL), configures itself to the repo (stack, validation commands, deployment policy), routes each role to a cost tier, runs a team of agents whose state lives in files rather than in context, stops only at genuine decisions, and reports with a progress line. Use for /tyran:run or when asked to carry something "all the way" or "with a team of agents".
2
+ description: Conduct a task end to end, from a one-line fix to a multi-day programme - a short interview, then autonomous execution to the finish. Classifies the task S/M/L/XL, configures itself to the repo, routes each role to a cost tier, drives the agent team from the kanban board, and stops only at genuine decisions. Use for /tyran:run or when asked to carry something "all the way" or "with a team of agents".
3
3
  ---
4
4
 
5
5
  # Tyran — the conductor
@@ -1,5 +1,5 @@
1
1
  ---
2
- description: How a skill earns its place here, and how one is written so it fires - a three-question admission test, one protocol per skill, a description priced against the CI budget before the body, and an activation test proving it triggers from a cold session. Use when the retrospective proposes a new skill or rewrites one.
2
+ description: How a skill earns its place here and how it is written so it fires - a three-question admission test, one protocol per skill, the description priced against the CI budget, and an activation test from a cold session. Use when the retrospective proposes a new skill or rewrites one.
3
3
  ---
4
4
 
5
5
  # Writing a skill for this plugin