@jjanczur/tyran 0.1.39 → 0.1.42

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": "0.1.42",
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": "0.1.42",
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 +1,230 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.1.42 — 2026-08-18
4
+
5
+ ### The board stopped throwing you off the page you were reading
6
+
7
+ Six defects, all reported by an operator using the board rather than found by
8
+ a test, and every one of them a place where the page knew something and did
9
+ not act on it.
10
+
11
+ **The tab lived in a local variable.** The page reloads itself every 30
12
+ seconds; tab state did not survive that, so anyone reading Spend was returned
13
+ to Overview twice a minute. The open tab now travels in the URL fragment, which
14
+ also makes `#questions` a link you can send someone. `replaceState`, not an
15
+ assignment to `location.hash` — the latter pushes a history entry per reload,
16
+ and Back then walks backwards through half an hour of refreshes instead of
17
+ leaving the page. A `hashchange` listener answers the other half: changing only
18
+ the fragment is a same-document navigation that reloads nothing, so without it
19
+ a deep link into an already-open page moved the URL and nothing else. That half
20
+ is invisible to source reading and was found in a browser.
21
+
22
+ **Spend now holds the refresh timer, as Settings already did.** Nothing on it
23
+ is live: it is one scan of your transcripts, and reloading under a reader
24
+ comparing two rows re-runs the scan to redraw numbers that did not move. The
25
+ lane filter holds it too, and releases when cleared. Overview and Board are
26
+ never held — a board that quietly stopped updating at midnight is the failure
27
+ this page exists to prevent.
28
+
29
+ **An initiative row is a button now.** It was the one thing on the page you
30
+ could read and not open. Selecting one opens the ticket detail's own shape:
31
+ directory, state, tickets merged, findings, when it last moved — and the
32
+ documents beside its journal, which the board has listed as paths since it
33
+ learned to list them and could not show.
34
+
35
+ `GET /doc.json?init=…&name=…` serves those five files, and it takes **no path**.
36
+ `name` must equal a member of `INITIATIVE_FILES`; `init` must equal a directory
37
+ `state/` actually contains. Nothing from the request is joined into a path
38
+ until it has matched one of those two lists, so traversal is refused by never
39
+ being a candidate rather than by a filter someone has to keep ahead of. The
40
+ text is invisible-escaped like every other journal-side value that reaches a
41
+ human, capped at 200 000 codepoints, and rendered by nothing — these documents
42
+ are agent-written, out of reports about other repositories. Reading is not
43
+ behind `--write`: that flag draws its line at changing the repository.
44
+
45
+ **Finished and abandoned stopped looking identical.** A percentage cannot tell
46
+ them apart, and the board had nothing else — measured across 63 real journals,
47
+ 43 sat on an unanswered question and 6 were genuinely done. A `checkpoint`
48
+ whose phase is the reserved word `closed` is the only event that ends an
49
+ initiative, and it already closes that initiative's open spawns; the row now
50
+ says `FINISHED`, carries the timestamp, sorts last and leaves the "waiting on
51
+ you" count. It is deliberately **not** a deployment claim: no event in the
52
+ closed set records a deploy, so the board does not imply one.
53
+
54
+ **The answer box grew the keystroke everyone tried.** ⌘/Ctrl+Enter sends, and
55
+ the placeholder says so — "Answer" was always the send button, but a labelled
56
+ verb beside a text box reads as a mode switch. Bare Enter still inserts a
57
+ newline, on purpose: answers are sentences, which is why the field is a
58
+ textarea, and what it sends is appended to a journal that can never take it
59
+ back.
60
+
61
+ **And the three `npx answer` commands folded away.** They are the only route on
62
+ a read-only board or one opened over `file://`, so they cannot be removed — but
63
+ above the questions on a writable board they were three commands you never need
64
+ in the place the eye lands first. They now sit behind "Answer from the terminal
65
+ instead", and open themselves on the boards where they are the answer, decided
66
+ by the `writable` flag the settings fetch already returned.
67
+
68
+ Documented on both surfaces, including the difference the page never explained:
69
+ a **default** is what happens if you say nothing (blank is recorded verbatim as
70
+ your decision), a **recommendation** is what the asking agent thinks you should
71
+ do (it fills the box and submits nothing).
72
+
73
+ ## 0.1.41 — 2026-08-18
74
+
75
+ ### The knowledge store can now shrink, and nothing is destroyed to do it
76
+
77
+ `.tyran/knowledge/` only ever grew. `knowledge.mjs audit` measured the damage
78
+ and said, in its own output, that nothing merges overlapping entries — true
79
+ since 0.1.35 corrected the three surfaces that had promised otherwise.
80
+
81
+ The producer everyone was waiting for turned out to be the wrong thing to
82
+ build. **`supersedes` was already in the schema, already documented, and read
83
+ by nothing.** Making `selectEntries` honour it turns a merge into an *append*:
84
+ write the entry that states the fact once, name the ones it replaces, touch
85
+ nothing else. The replaced entries stop reaching briefs immediately and keep
86
+ their bytes, their provenance and the counters they earned over months —
87
+ because no file holding them was edited.
88
+
89
+ That shape is the whole safety argument, and it is why no verifier shipped
90
+ alongside. A bad merge is not a lost history to be prevented by review; it is
91
+ one file to delete, after which every retired entry comes back whole.
92
+ Conservation checks — counters summed, provenance carried across — guard a
93
+ *lossy* merge that appending does not perform, and they cannot express the
94
+ risk that actually exists: the merged sentence dropping the important half.
95
+ Certifying the arithmetic while the meaning evaporates is the expensive kind
96
+ of false assurance.
97
+
98
+ **`supersedes` had to widen to a list first**, and that is probably why nothing
99
+ was ever built on it: as a scalar, a merged entry could retire exactly one
100
+ predecessor, so an N→1 merge — which is what consolidation *is* — could not be
101
+ written down at all. An entry may not supersede itself (the validator refuses
102
+ it; a flat suppression set would otherwise hide the entry carrying the
103
+ reference), and a mutually superseding pair hides both, so `audit` names those
104
+ rather than teaching the selector graph theory.
105
+
106
+ **No script decides which entries say the same thing.** That is a judgement and
107
+ it stays the retrospective's — text-similarity scoring was considered and cut,
108
+ because on a store this size the agent adjudicating the candidates reads them
109
+ better than a token score dominated by shared vocabulary. The line that fell
110
+ out is worth keeping: *a script may count a judgement already recorded; it may
111
+ not perform one.*
112
+
113
+ Which is what licensed the other half. `used`/`helpful`/`outdated_reports` are
114
+ report verdicts — recorded judgements — and three surfaces already instructed
115
+ an agent to retire entries on their evidence while **nothing computed it**: the
116
+ same unimplemented-promise defect as 0.1.35, one field over. `audit` now names
117
+ the candidates: reported wrong more often than helpful, or delivered three
118
+ times or more and never once helpful. An entry delivered *once* is never a
119
+ candidate; that is absence of evidence, not evidence.
120
+
121
+ The most useful line it prints is the degenerate one. The counters are
122
+ maintained only by a model hand-editing YAML at retro close, so if that fold is
123
+ not happening every entry reads `helpful: 0` and the rule would flag the entire
124
+ store — confidently, on nothing. A store with no counter evidence now reports
125
+ **that** instead, and flags nothing. Evidence is asked of the whole store
126
+ rather than the live part, or consolidating the one counter-bearing entry away
127
+ would flip the report to "the fold is not happening" — a strong claim, and
128
+ false.
129
+
130
+ Also: a duplicate entry id **across two files** went undetected, because the
131
+ validator allocates its id set per document and runs per file. It matters more
132
+ now that `supersedes` names an id — an ambiguous one retires whichever entry
133
+ the loop reached first. `loadEntries` refuses it through the channel `brief`
134
+ and `audit` already treat as loud.
135
+
136
+ That refusal is why it also earns a doctor finding, `knowledge-duplicate-id`
137
+ (error). The intent had been to add none — an overlap or staleness backlog is
138
+ a judgement queue rather than a malfunction, and would be red on every mature
139
+ store forever, which is the shape people learn to skip. A duplicate id is the
140
+ opposite: never red on a healthy store, and a genuine break. Without it doctor
141
+ reported a **healthy** repo whose every handoff got no brief at all, since
142
+ `brief` exits 1 on a store that does not validate. A gate that cannot fire is
143
+ the thing `doctor --state` exists to catch, so it could hardly be the thing it
144
+ stayed quiet about.
145
+
146
+ `doctor --state` counts live and superseded separately; pairing a
147
+ live-only reachability with an on-disk total would have printed "1 of 3 can
148
+ reach a brief; 0 cannot".
149
+
150
+ Both guard tests from 0.1.35 were **retuned, not removed**. The one banning
151
+ `/consolidat/i` from the audit was a proxy that expires the moment the step
152
+ exists, so it now asserts the property directly: the audit may describe the
153
+ mechanism only while a brief genuinely stops delivering a superseded entry —
154
+ checked by running a brief, not by grepping for a function name. The one
155
+ gating doc prose on an unimplemented feature had an escape hatch by design;
156
+ letting it fall silent would have traded a real guard for none, so it now
157
+ asserts the two self-improvement surfaces agree line for line. The original
158
+ defect was never that the claim existed — it was that one claim lived in three
159
+ places and drifted.
160
+
161
+ ### A finding names the command behind it, not a sentence about one
162
+
163
+ A `finding` carried `claim` + `proof`, and `proof` is prose — so the journal
164
+ recorded *"the parser rejects block scalars"* rather than anything the parser
165
+ did. That is a claim standing where evidence should be, which is the thing the
166
+ evidence gate already refuses in an implementer's report. Findings had a pass
167
+ on the same rule.
168
+
169
+ `finding` events now take **`command`** and **`exit_code`**. Both optional,
170
+ both projected into `STATE.md`'s Findings table.
171
+
172
+ **The ask was for the raw OUTPUT, and that was the expensive framing.** Three
173
+ things changed the answer. A stored output is a snapshot that rots and can
174
+ never be re-checked, while a command can be re-run by anyone who doubts the
175
+ claim. What the ask actually wanted was proof that a command ran at all —
176
+ which is the command and its exit code, not the bytes; on a long command the
177
+ bytes are noise. And the payload-size objection that made this an S–M turned
178
+ out not to exist: the cross board already carries findings as a **count**, and
179
+ the per-initiative `board.json` carries none. **Neither byte-compared artefact
180
+ changed** — verified by the goldens, where `BOARD.md` and `board.json` came
181
+ back byte-identical and only `STATE.md` moved. A test now states that rule for
182
+ `command` too, because it is the one field somebody will be tempted to promote
183
+ onto a card.
184
+
185
+ `command` is capped at **500** codepoints, an order of magnitude tighter than
186
+ the prose keys, and the number is measured rather than picked: this repo
187
+ documents 86 shell commands, median 74 codepoints, longest 123. Wide enough
188
+ for any real pipeline; too narrow to smuggle pasted output into a committed
189
+ file. Rejected at append, never truncated, like every other capped key.
190
+
191
+ The prompts had already got ahead of the schema — `agents/implementer.md`
192
+ tells an implementer to journal each dead hypothesis *"with the command output
193
+ that killed it"*, and `tyran:verifier`'s entire report is `command · exit code
194
+ · counts`. There was nowhere structured for either to land, so it went into
195
+ `proof` as prose. Now it has a home, and the implementer, verifier, scout,
196
+ reviewer and conductor prompts say so in one sentence each.
197
+
198
+ **What this does NOT do.** It does not tell a real command from an invented
199
+ one. A recorded command is still the agent's word — the same limit the
200
+ evidence gate prints about itself: *it blocks silence, not forgery.* What
201
+ changes is that the word is now specific and re-runnable instead of prose.
202
+ Verifying a command against the platform's own transcript is designed and
203
+ deliberately unbuilt; `NOTES-REQUESTS.md` §12.3 records the mechanism so it is
204
+ not re-derived.
205
+
206
+ Doctor gains **`finding-no-command`** (info): findings whose proof is prose
207
+ alone, counted and named. Info and not warning because every finding written
208
+ before this release predates the keys, and a check that goes red on upgrade
209
+ day is one people learn to skip. It is never a refusal — `journal.mjs` still
210
+ requires only `area` + `claim`, and a finding from reading code legitimately
211
+ has no command.
212
+
213
+ ## 0.1.40 — 2026-08-17
214
+
215
+ ### Every session pays for these sentences, so they got shorter
216
+
217
+ Fifteen of the nineteen descriptions — ten skills, five agents — rewritten to
218
+ carry only what routes: what it does, when it fires, the one distinguishing
219
+ mechanism. The justifications live in the bodies, which load only when the
220
+ skill fires. Skill total: **4352 → 3868 of 5000** (measured by the same CI
221
+ guard that enforces the cap); the agent descriptions, which the Agent tool
222
+ loads into every session the same way, shed a similar fraction.
223
+
224
+ Nothing lost its trigger — `prompt-tuning` GAINED one (it was the only
225
+ description with no "use when" clause), and `run`'s now names the kanban it
226
+ drives the team from, which 0.1.39 made true.
227
+
3
228
  ## 0.1.39 — 2026-08-17
4
229
 
5
230
  ### A fifth agent, and the conductor plans from the board it shows you
package/README.md CHANGED
@@ -57,7 +57,10 @@ asking you to describe it. After every initiative the team runs a retrospective
57
57
  on itself, and what it changes is Tyran, never your product code. The same
58
58
  failure three times becomes knowledge pasted into every matching handoff; five
59
59
  times and it becomes a rule in your `CLAUDE.md`, carrying the dates that earned
60
- it. Most retros correctly change nothing.
60
+ it. That knowledge does not only grow: entries the counters have written off
61
+ are retired on evidence, and two that say one thing are merged by appending a
62
+ third that supersedes both — the originals stay on disk, so an unwanted merge
63
+ is one file to delete. Most retros correctly change nothing.
61
64
 
62
65
  All of it lands on one page — a **board**: what every agent is doing right now,
63
66
  which questions are waiting on you (answer them there and the run carries on),
@@ -315,11 +318,11 @@ branch), `tyran:reviewer` (may fix what it finds, but editing forfeits
315
318
  suite on the cheapest tier, reports raw counts, never fixes), `tyran:retro`. A skill is admitted only when something already asks
316
319
  for the protocol by name, and every description is loaded into every session
317
320
  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
321
+ enforces the cap (3868 of 5000 characters). What each one assumes, when it
319
322
  fires and who invokes it, is in
320
323
  [skills and agents](https://jjanczur.github.io/tyran/skills/); the prompts
321
324
  themselves are in [`skills/`](skills/) and [`agents/`](agents/). Behind all of
322
- it: 1590 unit tests, run with `node --test "tests/**/*.test.mjs"`.
325
+ it: 1620 unit tests, run with `node --test "tests/**/*.test.mjs"`.
323
326
 
324
327
  ## Documentation
325
328
 
@@ -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.
@@ -38,7 +38,9 @@ commits and anything written to disk are in English.**
38
38
  thing you are about to write; if it exists, report it as a corrected
39
39
  premise instead of duplicating it. Durable discoveries worth another
40
40
  agent's time go into the journal as `finding` events (`area` + `claim`
41
- are required, plus its `proof`) — not only into prose.
41
+ are required, plus its `proof`) — not only into prose. When you found it
42
+ by RUNNING something, add `command` and `exit_code`: a command the next
43
+ agent can re-run outlives a sentence about what you saw.
42
44
  - **Verify the handoff's premises in the code.** A stale path, a wrong
43
45
  assignment, a function that no longer exists — correct it and report the
44
46
  correction EXPLICITLY instead of executing blindly. Premises about DATA
@@ -59,7 +61,8 @@ commits and anything written to disk are in English.**
59
61
  - **Two refuted hypotheses is the timebox.** When two named root-cause
60
62
  hypotheses have both been disproven and you do not have a third, stop:
61
63
  signal `blocked`, write what you RULED OUT into the journal as a
62
- `finding` — each dead hypothesis with the command output that killed it —
64
+ `finding` — each dead hypothesis with the `command` that killed it and its
65
+ `exit_code`, the output itself in your report —
63
66
  and report back. The ruled-out list IS the deliverable: the conductor
64
67
  re-routes the story with more reasoning or a stronger tier, and that
65
68
  agent starts where you stopped instead of at the wall. Handing back
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
@@ -73,12 +73,15 @@ next retro relitigating the same idea.
73
73
  report generators. A one-off harness from an initiative either becomes a
74
74
  general tool or gets deleted; do not leave dead files behind.
75
75
  - **Knowledge upkeep:** fold the reports' knowledge-brief verdicts into the
76
- entries' counters (the fold procedure lives in `skills/retro/SKILL.md`, under
77
- "Write down what is true about THIS repo" — one home, not two), and retire or
78
- split entries
79
- `doctor --state` flags as `knowledge-entry-oversized`. An entry whose
80
- counters say it stopped earning its keep is a deletion candidate, which
81
- satisfies the deletion preference.
76
+ entries' counters, consolidate what the store now says twice, and retire or
77
+ split entries `doctor --state` flags as `knowledge-entry-oversized` (all
78
+ three procedures live in `skills/retro/SKILL.md`, under "Write down what is
79
+ true about THIS repo" — one home, not two). `knowledge.mjs audit` names the
80
+ entries whose counters have written them off, and consolidating is merging
81
+ what you judge to be one fact — which satisfies the deletion preference.
82
+ Consolidation APPENDS an entry whose `supersedes:` names the ones it
83
+ replaces; you never edit or delete the originals, so a merge you got wrong
84
+ costs one deleted file rather than counters earned over months.
82
85
  - **The mistakes ledger:** append an entry to `MISTAKES.md` for every breakage
83
86
  this initiative actually paid for — what happened, the root cause, the
84
87
  consequence, the prevention — and give it a **signature** you reuse for the
@@ -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
 
@@ -63,7 +63,9 @@ sentence is a claim about evidence.
63
63
  2. **Run your OWN verification.** Do not believe the author's report — an
64
64
  author's report with no raw command output you reject on sight, without
65
65
  reading further. Run the tests yourself; for UI, drive the browser yourself
66
- through `browser-check`. Paste what you got, with counts.
66
+ through `browser-check`. Paste what you got, with counts. A `finding` you
67
+ journal carries the `command` and `exit_code` behind it, so the next reader
68
+ re-runs your evidence instead of trusting your sentence about it.
67
69
  - **Signal ONLY a blockage that genuinely stops the review** — a `progress`
68
70
  event with `state: "blocked"` (then `"unblocked"`) to the main checkout's
69
71
  journal, path from the handoff. Nothing else: your lease IS your
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
 
@@ -15,7 +15,8 @@ disk is in English.**
15
15
  side effect?" as a question you must be able to answer yes to before
16
16
  running it.
17
17
  2. **A finding is a claim plus its proof.** Every line you return is
18
- `finding -> path:line, quoted fragment, or URL`. The conductor reads dozens
18
+ `finding -> path:line, quoted fragment, URL, or the command you ran and what
19
+ it exited with`. The conductor reads dozens
19
20
  of these; there is no budget for warm-up paragraphs, and an unsourced
20
21
  finding costs more than no finding because someone will act on it. Prefix
21
22
  the ones that will outlive this task with `DURABLE:` — the conductor
@@ -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
 
@@ -14,7 +14,8 @@ disk is in English — though you should not be writing anything to disk.**
14
14
 
15
15
  1. **Run EXACTLY the commands the handoff names, in order.** No substitutes,
16
16
  no added flags, no "while I'm here". A command that does not exist in the
17
- repo is a finding to report, never a thing to install.
17
+ repo is a finding to report, never a thing to install — journalled with the
18
+ `command` you were handed and the `exit_code` you got.
18
19
  - Take the heavy-slot lease first when the handoff names one — a test
19
20
  suite is a heavy phase — and release it when you finish, including when
20
21
  you finish by failing.
package/bin/tyran.mjs CHANGED
@@ -78,7 +78,7 @@ export const COMMANDS = {
78
78
  ],
79
79
  knowledge: [
80
80
  'knowledge.mjs',
81
- 'Select the knowledge entries that apply to a set of paths and print a paste-ready brief for a handoff.',
81
+ 'Brief the knowledge entries that apply to a set of paths, or audit the store for what no brief can reach.',
82
82
  ],
83
83
  mistakes: [
84
84
  'mistakes.mjs',
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@jjanczur/tyran",
3
- "version": "0.1.39",
3
+ "version": "0.1.42",
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": {
@@ -9,6 +9,9 @@
9
9
  "bin": {
10
10
  "tyran": "./bin/tyran.mjs"
11
11
  },
12
+ "scripts": {
13
+ "test": "node --test \"tests/**/*.test.mjs\""
14
+ },
12
15
  "publishConfig": {
13
16
  "access": "public"
14
17
  },