@jjanczur/tyran 0.1.40 → 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.
- package/.claude-plugin/marketplace.json +1 -1
- package/.claude-plugin/plugin.json +1 -1
- package/CHANGELOG.md +210 -0
- package/README.md +5 -2
- package/agents/implementer.md +5 -2
- package/agents/retro.md +9 -6
- package/agents/reviewer.md +3 -1
- package/agents/scout.md +2 -1
- package/agents/verifier.md +2 -1
- package/bin/tyran.mjs +1 -1
- package/package.json +4 -1
- package/scripts/board-html.mjs +264 -19
- package/scripts/board.mjs +134 -6
- package/scripts/doctor.mjs +116 -4
- package/scripts/journal.mjs +17 -1
- package/scripts/knowledge.mjs +219 -20
- package/scripts/project.mjs +9 -1
- package/scripts/schema.mjs +37 -2
- package/skills/retro/SKILL.md +26 -0
- package/skills/run/SKILL.md +4 -2
- package/templates/knowledge.yaml +5 -0
|
@@ -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.
|
|
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.
|
|
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 +1,215 @@
|
|
|
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
|
+
|
|
3
213
|
## 0.1.40 — 2026-08-17
|
|
4
214
|
|
|
5
215
|
### Every session pays for these sentences, so they got shorter
|
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.
|
|
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),
|
|
@@ -319,7 +322,7 @@ 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:
|
|
325
|
+
it: 1620 unit tests, run with `node --test "tests/**/*.test.mjs"`.
|
|
323
326
|
|
|
324
327
|
## Documentation
|
|
325
328
|
|
package/agents/implementer.md
CHANGED
|
@@ -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
|
|
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
|
@@ -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
|
|
77
|
-
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
counters
|
|
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
|
package/agents/reviewer.md
CHANGED
|
@@ -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
|
@@ -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
|
|
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
|
package/agents/verifier.md
CHANGED
|
@@ -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
|
-
'
|
|
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.
|
|
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
|
},
|