@jjanczur/tyran 0.1.14 → 0.1.18
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 +212 -0
- package/README.md +7 -1
- package/agents/implementer.md +15 -3
- package/agents/reviewer.md +7 -0
- package/bin/tyran.mjs +8 -0
- package/hooks/scripts/policy-gate.mjs +374 -8
- package/hooks/scripts/session-start.mjs +69 -2
- package/package.json +1 -1
- package/scripts/answer.mjs +896 -0
- package/scripts/board-html.mjs +194 -0
- package/scripts/board.mjs +35 -3
- package/scripts/cost.mjs +811 -0
- package/scripts/doctor.mjs +65 -0
- package/scripts/journal.mjs +79 -1
- package/scripts/overnight.mjs +4 -2
- package/scripts/project.mjs +15 -3
- package/scripts/scan-repo.mjs +11 -0
- package/scripts/schema.mjs +89 -1
- package/scripts/tiers.mjs +17 -0
- package/skills/run/SKILL.md +27 -6
- package/templates/config.yaml +21 -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": "0.1.18",
|
|
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": "0.1.18",
|
|
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 +1,217 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 0.1.18 — 2026-08-14
|
|
4
|
+
|
|
5
|
+
### The spend ledger: nobody could say what a run cost
|
|
6
|
+
|
|
7
|
+
`node scripts/cost.mjs` reports what the work cost, in tokens the platform
|
|
8
|
+
itself reported, per model, per agent type and per ticket. It **reads, it never
|
|
9
|
+
instruments**: every number comes from the `message.usage` records Claude Code
|
|
10
|
+
already writes under `~/.claude/projects/`, so there is no hook, no probe, no
|
|
11
|
+
new event type and nothing to keep in sync.
|
|
12
|
+
|
|
13
|
+
It is deliberately **not a projection**, and that is the decision the rest
|
|
14
|
+
follows from. Its inputs are machine-local and differ per clone, so two people
|
|
15
|
+
with the same journal legitimately get different numbers — which is exactly
|
|
16
|
+
what a byte-exact `--check` would report as drift. `cost.json` is therefore
|
|
17
|
+
never committed (it joins the runtime files `.tyran/.gitignore` excludes),
|
|
18
|
+
never byte-compared, and never merged into `board.json`.
|
|
19
|
+
|
|
20
|
+
**Tokens are facts; money is an opinion.** Only tokens are counted. Money comes
|
|
21
|
+
from an operator-written `pricing:` block, and the card's name travels with
|
|
22
|
+
every amount — a figure that cannot say which card produced it is not a
|
|
23
|
+
measurement. Absent pricing gives tokens and no money, which is the honest
|
|
24
|
+
default: Tyran does not know what anyone pays. All four rate keys are required
|
|
25
|
+
per model, because a table carrying three would price the fourth at zero,
|
|
26
|
+
silently, and cache reads alone were measured at roughly three quarters of a
|
|
27
|
+
real session's cost.
|
|
28
|
+
|
|
29
|
+
Gaps are reported rather than zeroed: `unpriced` models are counted in tokens
|
|
30
|
+
and absent from every amount, `unattributed` agents are the ones whose task
|
|
31
|
+
description carried no ticket id, `unreadable` transcripts are named. A model
|
|
32
|
+
that billed zero tokens is not reported as unpriced — that would be a permanent
|
|
33
|
+
false warning about something that cannot cost anything. And partial pricing is
|
|
34
|
+
a partial sum: an amount is blank only when nothing in the row is priced at
|
|
35
|
+
all, because a real rate card always misses something and nulling the grand
|
|
36
|
+
total over one absent row would leave every figure blank forever.
|
|
37
|
+
|
|
38
|
+
The conductor is its own row. Its context is not attributable to any ticket and
|
|
39
|
+
was measured between 44% and 86% of a tree's tokens, so a per-ticket table that
|
|
40
|
+
omitted it would present a fraction of the bill as the cost of the work. That
|
|
41
|
+
share is reported in tokens, never dollars: a partial rate card prices only some
|
|
42
|
+
models, so a dollar share is a ratio over whichever subset happened to be
|
|
43
|
+
priced — the same tree read 86% by tokens and 99% by dollars.
|
|
44
|
+
|
|
45
|
+
Ticket attribution cost nothing to add. The conductor already puts the ticket id
|
|
46
|
+
at the head of a `Task` description; the reader takes it back out of the agent's
|
|
47
|
+
`.meta.json`. No journal change, no event-set change, and an agent whose
|
|
48
|
+
description omits the id lands in a visible `unattributed` bucket rather than
|
|
49
|
+
being guessed at.
|
|
50
|
+
|
|
51
|
+
`board.html` gains a **Spend** section, and it **fetches `cost.json` rather than
|
|
52
|
+
embedding it** — a deliberate amendment to the page's "self-contained, no
|
|
53
|
+
network" description. It is still zero external hosts and zero CDNs; what it
|
|
54
|
+
makes is one same-origin request to loopback. Over `file://` there is no server,
|
|
55
|
+
the request fails, and the section never appears, so `board.json` and
|
|
56
|
+
`board.html` keep their byte-exact `--check` contract and carry no machine-local
|
|
57
|
+
data. The `/cost.json` route is covered by the existing `Host` pin (a foreign
|
|
58
|
+
`Host` gets 403, verified) and returns 503 rather than taking the board down if
|
|
59
|
+
the cost read fails.
|
|
60
|
+
|
|
61
|
+
Transcripts reach tens of megabytes and the page refreshes every 30 seconds, so
|
|
62
|
+
the reader streams in chunks and caches per source file keyed on `(path, mtime,
|
|
63
|
+
size)`. A finished agent's transcript never changes, so only the running
|
|
64
|
+
session's file is re-read. Measured cold: a 226-transcript tree totalling 6.86
|
|
65
|
+
billion tokens scans in 1.7 s.
|
|
66
|
+
|
|
67
|
+
Also reachable as `npx @jjanczur/tyran cost`. Exit 0 ok · 2 usage, I/O, or no
|
|
68
|
+
transcripts found — spend is read, and nothing here estimates it.
|
|
69
|
+
|
|
70
|
+
**Upgrading: regenerate your board.** `board.html` gained the Spend section, so
|
|
71
|
+
its BYTES changed even though its contract did not. A repo that committed a
|
|
72
|
+
board rendered by an earlier version will see `board.mjs --check` report drift —
|
|
73
|
+
and `doctor --state` report `projection-drift` — until you run
|
|
74
|
+
`node scripts/board.mjs --dir .tyran` and commit the result. `board.json` and
|
|
75
|
+
`BOARD.md` are byte-identical to 0.1.17.
|
|
76
|
+
|
|
77
|
+
## 0.1.17 — 2026-08-14
|
|
78
|
+
|
|
79
|
+
### A race test that picked a winner
|
|
80
|
+
|
|
81
|
+
`two apply runs at once cannot both close one ask` accepted only two of the
|
|
82
|
+
three exits its own race can produce. On a runner slow enough to serialise
|
|
83
|
+
the two spawns, the first closes the queue and the second finds it empty and
|
|
84
|
+
exits 1 — correct behaviour, asserted as a failure. It passed locally and in
|
|
85
|
+
the PR checks and failed in the publish job, which is where a timing
|
|
86
|
+
assumption usually surfaces, and it kept 0.1.15 and 0.1.16 off npm although
|
|
87
|
+
both are merged and tagged.
|
|
88
|
+
|
|
89
|
+
All three exits are now accepted, and the guarantee is asserted where it
|
|
90
|
+
holds regardless of who won: no ask closed twice and no question closed by
|
|
91
|
+
two gates, checked while the racing runs are the only writers, then
|
|
92
|
+
completeness after one sequential settling run. Dropping the sitting lock
|
|
93
|
+
still fails the test.
|
|
94
|
+
|
|
95
|
+
## 0.1.16 — 2026-08-14
|
|
96
|
+
|
|
97
|
+
### `cat hooks/…` was refused while `Read` handed you the same bytes
|
|
98
|
+
|
|
99
|
+
Measured on the shipped 0.1.15 gate, on one file under `hooks/**`: `Read` passes,
|
|
100
|
+
and `cat`, `grep -n`, `wc -l` and `node --check` on that same file all **deny**.
|
|
101
|
+
The bytes were one tool call away in every case, so the refusal protected
|
|
102
|
+
nothing — and it was not consistent with itself either: `git log --oneline --
|
|
103
|
+
hooks/` passed all along, because a bare directory token names no file to
|
|
104
|
+
classify, while `wc -l` on a file inside it did not. The cost was four
|
|
105
|
+
interrupted tool calls in one session for the author, every one of them while
|
|
106
|
+
reading the gate being worked on.
|
|
107
|
+
|
|
108
|
+
The rule this release encodes instead: **the shell must not become a second
|
|
109
|
+
route to something the `Read` tool already refuses.** For `.env` that symmetry
|
|
110
|
+
is load-bearing and is untouched — `Read` denies *and* `grep` denies, because
|
|
111
|
+
the measured incident behind that rule is a refused `Read .env` followed by
|
|
112
|
+
`Bash: grep` in the very next tool call. Where `Read` is allowed, refusing the
|
|
113
|
+
shell buys nothing.
|
|
114
|
+
|
|
115
|
+
So on `hooks/**` and `.tyran/policies/**` — and only there — a read-only shell
|
|
116
|
+
command now passes. "Read-only" is matched on the **program and its flags**,
|
|
117
|
+
never on the program alone, because read-shaped programs have write-shaped
|
|
118
|
+
modes: `node --check FILE` passes and `node FILE` denies; `git log` passes and
|
|
119
|
+
`git log --output=FILE` denies, which was a real hole found in an earlier review
|
|
120
|
+
of this gate; `tail -n 5` passes and `tail -f` does not. An unrecognised flag
|
|
121
|
+
refuses, so the enumeration's incompleteness costs a false refusal and never a
|
|
122
|
+
pass. `sed` and `awk` are not on the list at all: their script argument is a
|
|
123
|
+
program with its own write commands, and reading it would need a second parser.
|
|
124
|
+
The raw command may contain none of ``< > $ ` ( ) { } &``, which is every
|
|
125
|
+
redirection spelling, command substitution, subshell and `&&` at once — checked
|
|
126
|
+
on the raw text, because the shared lexer *consumes* those characters as
|
|
127
|
+
separators and by the time a token exists the `>` is gone. `|` and `;` are fine,
|
|
128
|
+
since each composed segment still has to be an allowed reader.
|
|
129
|
+
|
|
130
|
+
What did not change: every credential shape denies for reads and writes alike;
|
|
131
|
+
`.claude/settings.json` and `.claude/settings.local.json` stay refused from a
|
|
132
|
+
shell in every mode, which is a deliberate narrowing rather than a consequence —
|
|
133
|
+
`Read` passes on the registry too, so the principle alone would have admitted it,
|
|
134
|
+
and it is the one file from which every gate is switched off at once. One line
|
|
135
|
+
naming a readable path *and* a secret is still refused for the secret.
|
|
136
|
+
|
|
137
|
+
That last sentence needed a second check to stay true, and review found it out.
|
|
138
|
+
The exemption was decided on the **finding list**, which is computed from a
|
|
139
|
+
*stripped* copy of the command: `stripMessageArguments` removes a message-bearing
|
|
140
|
+
flag together with its argument, and non-literal tokens are dropped after that.
|
|
141
|
+
`-t` is `git commit --template` *and* a legal flag of `diff` and `cat`, so
|
|
142
|
+
`diff -t .env hooks/scripts/policy-gate.mjs` left a finding list naming only the
|
|
143
|
+
readable path, read as "read-only command on a readable path", and was exempted —
|
|
144
|
+
really publishing the file. Four shapes were measured deny-on-0.1.15 →
|
|
145
|
+
pass-before-the-fix: `diff -t SECRET FILE`, `grep --file=SECRET FILE`,
|
|
146
|
+
`grep -m SECRET FILE`, and `diff ~/SECRET FILE`, the last because a leading `~`
|
|
147
|
+
makes the token non-literal and it is dropped entirely. The exemption is now
|
|
148
|
+
refused when any word of the **raw** command is credential-shaped, tested with
|
|
149
|
+
the same `SECRET_READ_RULES` the findings use, and the refusal names that word
|
|
150
|
+
rather than offering a rewrite that cannot help. This is the invariant being
|
|
151
|
+
repaired, not a new capability: `diff -t .env src/app.js` publishes the same
|
|
152
|
+
bytes and always did, because it names no protected path at all. One false
|
|
153
|
+
refusal comes with it, in the safe direction — `git log --grep=.env -- FILE`
|
|
154
|
+
loses the exemption over a word in a search pattern.
|
|
155
|
+
|
|
156
|
+
The residual floor is stated in the refusal text and in `docs/policy-gate.md`
|
|
157
|
+
rather than implied: matching flags bounds what a command *says*, not what the
|
|
158
|
+
program *does*. An allowed reader can still be pointed at another program by
|
|
159
|
+
configuration this gate never reads — a `diff.external` driver or a pager in git
|
|
160
|
+
config, a `NODE_OPTIONS` carrying `--require`, a shell function shadowing `cat`.
|
|
161
|
+
That is the fifth entry in `SHELL_DECLARED_MISSES`. The sixth is one step
|
|
162
|
+
earlier: the program table is keyed on the **basename**, which is what makes
|
|
163
|
+
`/bin/cat` and `cat` one entry and also makes a repo-writable `src/cat` an
|
|
164
|
+
allowed reader. It is declared rather than closed, because closing it would
|
|
165
|
+
close nothing — a script with the path already inside it needs no allowed name
|
|
166
|
+
at all, which is the third entry.
|
|
167
|
+
|
|
168
|
+
## 0.1.15 — 2026-08-14
|
|
169
|
+
|
|
170
|
+
### Fifteen questions, ten minutes, and the swarm moves
|
|
171
|
+
|
|
172
|
+
An agent that hits a product decision no longer stops and waits for you. It
|
|
173
|
+
raises the question — `journal.mjs ask`, one command, which mints the id under
|
|
174
|
+
the journal's write lock so two agents asking at the same moment get two
|
|
175
|
+
questions rather than one — states what it recommends and what should ship if
|
|
176
|
+
nobody ever answers, and takes the next ticket. The question is a `gate` whose
|
|
177
|
+
`kind` IS its id, `Q-<n>`: the closed event set stays at 17, the board's
|
|
178
|
+
waiting-on-you queue already rendered it, and `answered` was already a pass
|
|
179
|
+
result. What was missing was an identity and a way in.
|
|
180
|
+
|
|
181
|
+
The way in is a text file. `tyran answer render` writes `.tyran/state/ANSWERS.md`
|
|
182
|
+
— every open question across every initiative, the ones with no recorded default
|
|
183
|
+
first, because those are the only ones where saying nothing has no safe outcome.
|
|
184
|
+
You type under `answer:`. **Blank accepts the recorded default**, verbatim, and
|
|
185
|
+
still records it as a decision; `-` leaves it for next time; anything else is your
|
|
186
|
+
answer in your own words. `tyran answer apply` folds them back as `decision` +
|
|
187
|
+
`gate result: answered` pairs — decision first, so a crash leaves a visible orphan
|
|
188
|
+
decision rather than a closed question whose answer was never written down — then
|
|
189
|
+
re-renders every projection and the board. It reads the question, the default and
|
|
190
|
+
the ticket back out of the journal, never out of the sheet, and it is
|
|
191
|
+
all-or-nothing: one unparseable block and nothing at all is appended, with the
|
|
192
|
+
line number.
|
|
193
|
+
|
|
194
|
+
Answering a question no longer needs the conductor to be awake. `SessionStart`
|
|
195
|
+
records the session id in `.tyran/state/conductor.json`, so `apply --resume` can
|
|
196
|
+
put the swarm back on it — and refuses while that session is still alive, because
|
|
197
|
+
two conductors on one journal is a hazard this repo has already paid for once.
|
|
198
|
+
|
|
199
|
+
One correction found while building it. Parking an asked ticket **hid** it: the
|
|
200
|
+
board checks a `ticket.status` override before the ask, so our own demo fixture
|
|
201
|
+
showed `waiting-operator (0)` with a question open — the fixture is corrected and
|
|
202
|
+
the skill now forbids the override.
|
|
203
|
+
|
|
204
|
+
Also: `question`, `recommendation`, `default` and `answer` are capped at 2000
|
|
205
|
+
codepoints (rejected, never truncated — historical oversizes stay warnings);
|
|
206
|
+
`STATE.md`'s open-gates table and the SessionStart probe now carry the question
|
|
207
|
+
text, so a resumed conductor sees *what* it asked and not merely that it is
|
|
208
|
+
waiting; doctor gains `ask-open` (info) and `ask-stale` (warning, 72 h); the gate
|
|
209
|
+
pass set has one spelling again, exported from `project.mjs` and imported by
|
|
210
|
+
`overnight.mjs` instead of hand-copied; `tiers` gains an advisory `conductor`
|
|
211
|
+
role with a `deep` floor, so the coordinator's model is named in the one file
|
|
212
|
+
where model names may live — and says on stderr that no plugin can change your
|
|
213
|
+
own session's model.
|
|
214
|
+
|
|
3
215
|
## 0.1.14 — 2026-08-14
|
|
4
216
|
|
|
5
217
|
### The repository remembers what went wrong — and eventually writes it into law
|
package/README.md
CHANGED
|
@@ -359,13 +359,14 @@ Published on npm as [`@jjanczur/tyran`](https://www.npmjs.com/package/@jjanczur/
|
|
|
359
359
|
command stays `tyran` either way; only the registry name is scoped, the same
|
|
360
360
|
pattern as `@angular/cli` giving you `ng`. `bin/tyran.mjs` exposes the same
|
|
361
361
|
scripts the plugin's hooks and skills already call — `doctor`, `scan-repo`,
|
|
362
|
-
`tiers`, `journal`, `schema`, `knowledge`, `board`, `overnight`, `statusline`, `stop-check`,
|
|
362
|
+
`tiers`, `journal`, `schema`, `knowledge`, `board`, `cost`, `answer`, `overnight`, `statusline`, `stop-check`,
|
|
363
363
|
`scan-control-chars`, `desc-budget` — for a shell or a CI job with no Claude
|
|
364
364
|
Code session. Zero dependencies; `--help` lists them.
|
|
365
365
|
|
|
366
366
|
```bash
|
|
367
367
|
npx @jjanczur/tyran doctor --hooks # is any gate installed but unable to fire?
|
|
368
368
|
npx @jjanczur/tyran scan-repo --dir . # what this repo looks like, with provenance
|
|
369
|
+
npx @jjanczur/tyran answer render # the sheet of questions waiting on you
|
|
369
370
|
```
|
|
370
371
|
|
|
371
372
|
Exit codes propagate to the digit, so a CI step reddens exactly when the
|
|
@@ -443,6 +444,11 @@ underlying script does.
|
|
|
443
444
|
- [x] Read-only dashboard: the kanban board — `BOARD.md`/`board.json` next to
|
|
444
445
|
every journal, one cross-initiative `board.html` in the landing page's
|
|
445
446
|
own palette, refreshed on every subagent stop, plus `board.mjs --serve`
|
|
447
|
+
- [x] The spend ledger: what the work actually cost, read out of the
|
|
448
|
+
transcripts Claude Code already writes — tokens per model, per agent type
|
|
449
|
+
and per ticket, money only under a rate card you write, and a Spend
|
|
450
|
+
section the board fetches rather than embeds — see
|
|
451
|
+
[docs/cost.md](docs/cost.md)
|
|
446
452
|
- [x] The mistakes ledger: `MISTAKES.md` at your repo root — what went wrong
|
|
447
453
|
here and how often — where three occurrences of one signature graduate a
|
|
448
454
|
lesson into `.tyran/knowledge/` and five write a rule into your
|
package/agents/implementer.md
CHANGED
|
@@ -48,9 +48,21 @@ commits and anything written to disk are in English.**
|
|
|
48
48
|
the prediction written down first, and name the mechanism. A fix for a
|
|
49
49
|
failure you never reproduced cannot be shown to have worked.
|
|
50
50
|
- When the PR comes back with comments, follow `pr-feedback`.
|
|
51
|
-
3. **Decide technical questions yourself.**
|
|
52
|
-
|
|
53
|
-
|
|
51
|
+
3. **Decide technical questions yourself.** "Shall I continue?" is forbidden.
|
|
52
|
+
A product or visual decision, or one that would cross a boundary the handoff
|
|
53
|
+
named, is not yours to make — and it is also not a reason to sit still.
|
|
54
|
+
Raise it as an operator ask, in one command, against the MAIN checkout's
|
|
55
|
+
journal (the handoff carries its absolute path):
|
|
56
|
+
`node ${CLAUDE_PLUGIN_ROOT}/scripts/journal.mjs ask <abs-journal> <init>
|
|
57
|
+
--actor <you> --ticket <your ticket> --question '...' --recommendation '...'
|
|
58
|
+
--default '...'`. State both: what you would do, and what should ship if
|
|
59
|
+
nobody ever answers. Then **carry on under your own default** if the story
|
|
60
|
+
can proceed, or report and end if it cannot. The `Q-<n>` the command prints
|
|
61
|
+
goes in your report. Do **not** set `ticket.status` — the ask already moves
|
|
62
|
+
your ticket into the board's waiting-operator lane, and an override on top
|
|
63
|
+
of it hides the question. Ask the **conductor**, not the operator, for a
|
|
64
|
+
technical unblock: a lease, a corrected premise, a scope call inside the
|
|
65
|
+
handoff.
|
|
54
66
|
4. **Shared zones are append-only**, per the manifest. `git add` takes an
|
|
55
67
|
explicit list of paths — never `-A`, never `.`; they sweep in files
|
|
56
68
|
belonging to other windows, and that has already put blobs on a remote
|
package/agents/reviewer.md
CHANGED
|
@@ -59,6 +59,13 @@ that keeps you.
|
|
|
59
59
|
review.
|
|
60
60
|
- When you find nothing, say so plainly. Manufacturing findings to look
|
|
61
61
|
thorough wastes a round and trains the conductor to discount you.
|
|
62
|
+
- A blocker that is really a **product or visual decision** is not a review
|
|
63
|
+
verdict. Raise it as an operator ask —
|
|
64
|
+
`node ${CLAUDE_PLUGIN_ROOT}/scripts/journal.mjs ask <abs-journal> <init>
|
|
65
|
+
--actor <you> --ticket <the ticket> --question '...' --recommendation
|
|
66
|
+
'...' --default '...'` — name the `Q-<n>` in your review, and give a
|
|
67
|
+
verdict on everything else. Holding a whole review open on one question
|
|
68
|
+
the operator has not seen is how a queue becomes a stall.
|
|
62
69
|
5. **Say what you did NOT check.** Platform you did not run on, concurrency
|
|
63
70
|
you did not exercise, the input class you skipped. This section is a merge
|
|
64
71
|
gate, not a courtesy: the conductor resolves every item as measured,
|
package/bin/tyran.mjs
CHANGED
|
@@ -88,6 +88,14 @@ export const COMMANDS = {
|
|
|
88
88
|
'board.mjs',
|
|
89
89
|
'Render the cross-initiative kanban board — BOARD.md, board.json and the board.html dashboard — from the journals under .tyran/state/.',
|
|
90
90
|
],
|
|
91
|
+
cost: [
|
|
92
|
+
'cost.mjs',
|
|
93
|
+
'What the work cost, in tokens the platform reported — per model, per agent type and per ticket, priced by your own rate card.',
|
|
94
|
+
],
|
|
95
|
+
answer: [
|
|
96
|
+
'answer.mjs',
|
|
97
|
+
'Write the sheet of questions waiting on you, then fold your answers back into the journal.',
|
|
98
|
+
],
|
|
91
99
|
'stop-check': [
|
|
92
100
|
'stop-check.mjs',
|
|
93
101
|
'Check the .tyran/STOP operator brake that halts a running initiative before its next spawn or merge.',
|