Every page tagged advise. Tags cut across the directory tree, so these pages come from different sections.
absoluteAn advisory by default: it explains, and blocks nothing, on never, nobody or nothing as a claim about the past ("has never fired", "nobody checked").
agreement-openerAn advisory by default: it explains, and blocks nothing, on an agent reply that opens with praise or agreement ("Great question", "You're right").
all-capsAn advisory by default: it explains, and blocks nothing, on words in capitals for emphasis in a review reply ("DO NOT", "NEVER").
bare-imperativeAn advisory by default: it explains, and blocks nothing, on a short command in a review reply that gives no reason anywhere ("Fix this.").
blameAn advisory by default: it explains, and blocks nothing, on a person or past work as the subject of a fault, and contempt for code or a decision.
bold-labelAn advisory by default: it explains, and blocks nothing, on list items or paragraphs of an agent reply that open with a bold label.
buzzword-weakAn advisory by default: it explains, and blocks nothing, on a buzzword that also has an ordinary sense ("crucial", "landscape").
changelog-entryAn advisory by default: it explains, and blocks nothing, on a changelog entry that names a Go identifier and says little else.
changelog-groupAn advisory by default: it explains, and blocks nothing, on a changelog heading that is not Added, Changed, Deprecated, Removed, Fixed or Security.
claimAn advisory by default: it explains, and blocks nothing, on a measurement, a comparison or a completion with no evidence in its sentence or bullet.
closing-offerAn advisory by default: it explains, and blocks nothing, on an agent reply whose last paragraph offers more work or asks leave to go on.
compat-marker: a leased worker adding a marker that keeps code for older data or callersAn advisory by default: it explains, and blocks nothing, on a leased worker adding a marker that keeps code for older data or callers.
creditAn advisory by default: it explains, and blocks nothing, on a change description that removes or replaces something and says nothing of what it was for.
echo-on-success: an `&& echo` that restates what the exit status already saysAn advisory by default: it explains, and blocks nothing, on an `&& echo` that restates what the exit status already says.
fillerAn advisory by default: it explains, and blocks nothing, on throat-clearing ("Note that") and filler adverbs ("simply", "basically").
focus: a read or write outside the paths the running job declaredAn advisory by default: it explains, and blocks nothing, on a read or write outside the paths the running job declared.
graph-stale: a graph read, or a graph-backed deny, while the graph describes another treeAn advisory by default: it explains, and blocks nothing, on a graph read, or a graph-backed deny, while the graph describes another tree.
guard-unfinished: guard checks that never finished, so no rule judged their callsAn advisory by default: it explains, and blocks nothing, on guard checks that never finished, so no rule judged their calls.
heading-caseAn advisory by default: it explains, and blocks nothing, on a heading whose every word after the first is capitalized.
hedgeAn advisory by default: it explains, and blocks nothing, on a softener qualifying a claim ("might fix", "could potentially").
hook-wiring: a write to the host wiring that decides whether these rules run at allAn advisory by default: it explains, and blocks nothing, on a write to the host wiring that decides whether these rules run at all.
instruction-write: a write to a cross-host instruction file, which every session loads wholeAn advisory by default: it explains, and blocks nothing, on a write to a cross-host instruction file, which every session loads whole.
issue-reproAn advisory by default: it explains, and blocks nothing, on a bug report with neither what happened against what was expected, nor steps to reproduce it.
judgment-as-factAn advisory by default: it explains, and blocks nothing, on a recommendation in a review reply stated as a fact, with no reason given.
leakAn advisory by default: it explains, and blocks nothing, on residue of a tool or a template: a citation marker or an unfilled placeholder.
lease-state: a leased write while its row reports a diverged base, a re-entered path, or a bad patternAn advisory by default: it explains, and blocks nothing, on a leased write while its row reports a diverged base, a re-entered path, or a bad pattern.
lease-terminal: a call naming a lease whose row has already finishedAn advisory by default: it explains, and blocks nothing, on a call naming a lease whose row has already finished.
leased-path: a write into paths a running lease owns, by a caller that names no leaseAn advisory by default: it explains, and blocks nothing, on a write into paths a running lease owns, by a caller that names no lease.
long-threadAn advisory by default: it explains, and blocks nothing, on a review reply that is its author's fourth or later in a thread.
new-file: a new file in a directory whose naming has settledAn advisory by default: it explains, and blocks nothing, on a new file in a directory whose naming has settled.
new-source-dir: a new file that opens a directory, which is a boundary rather than a fileAn advisory by default: it explains, and blocks nothing, on a new file that opens a directory, which is a boundary rather than a file.
nominalizationsAn advisory by default: it explains, and blocks nothing, on a text whose verbs are turned into nouns (validation, agreement, stability) at a generated-writing rate.
nonspecificAn advisory by default: it explains, and blocks nothing, on a top-level review comment that judges or asks for a change and names no code, path, line, example or reason.
participlesAn advisory by default: it explains, and blocks nothing, on a text that hangs present participial clauses on its sentences at a generated-writing rate.
precedent-search: a hunt for one distinctive name, which refs answers with verified sitesAn advisory by default: it explains, and blocks nothing, on a hunt for one distinctive name, which refs answers with verified sites.
push-gate: a push or `gh pr create` the run log cannot prove ungated; names the gateAn advisory by default: it explains, and blocks nothing, on a push or `gh pr create` the run log cannot prove ungated; names the gate.
read-symbol: a bounded read inside one indexed declaration, which refs --definition --source prints checkedAn advisory by default: it explains, and blocks nothing, on a bounded read inside one indexed declaration, which refs --definition --source prints checked.
regen-source: a hand edit to a file a target regeneratesAn advisory by default: it explains, and blocks nothing, on a hand edit to a file a target regenerates.
release-requested: a job holding write paths another fork was refused for, with a release request openAn advisory by default: it explains, and blocks nothing, on a job holding write paths another fork was refused for, with a release request open.
repeated-marksAn advisory by default: it explains, and blocks nothing, on a run of question or exclamation marks in a review reply ("??", "!!", "?!").
reply-openerAn advisory by default: it explains, and blocks nothing, on a sentence of a review reply that opens by contradicting ("No,", "As I said").
reply-voiceAn advisory by default: it explains, and blocks nothing, on text that answers a prompt the reader never saw: a reply opener, a bold-label item, a stock label.
request-recapAn advisory by default: it explains, and blocks nothing, on an agent reply that opens by restating what the person asked.
revert-classify: a revert that has not classified what it is revertingAn advisory by default: it explains, and blocks nothing, on a revert that has not classified what it is reverting.
scope-drift: a write into a project this session has no dependency edge toAn advisory by default: it explains, and blocks nothing, on a write into a project this session has no dependency edge to.
shared-checkout: a spawn into a checkout a live job already holds and writesAn advisory by default: it explains, and blocks nothing, on a spawn into a checkout a live job already holds and writes.
short-reply-headingAn advisory by default: it explains, and blocks nothing, on a heading in an agent reply under 300 words.
signpostAn advisory by default: it explains, and blocks nothing, on an announcement standing where the point should be ("Here's the thing", "Let's dive in").
skill-source: a write to an installed skill copy rather than to its sourceAn advisory by default: it explains, and blocks nothing, on a write to an installed skill copy rather than to its source.
source-read: an unbounded source read the symbol index has already answeredAn advisory by default: it explains, and blocks nothing, on an unbounded source read the symbol index has already answered.
spawn-unplaced: a subagent's first call that no waiting spawn names, which then runs under no leaseAn advisory by default: it explains, and blocks nothing, on a subagent's first call that no waiting spawn names, which then runs under no lease.
split-run: the same target run again on a different project set, as a separate callAn advisory by default: it explains, and blocks nothing, on the same target run again on a different project set, as a separate call.
stacked-hedgeAn advisory by default: it explains, and blocks nothing, on two softeners in one sentence of a review reply, or an apology before its point.
stage-classify: staging without classifying, when generated and source differAn advisory by default: it explains, and blocks nothing, on staging without classifying, when generated and source differ.
subject-moodAn advisory by default: it explains, and blocks nothing, on a commit subject opening in the past tense, the third person or a gerund ("added", "fixes", "making").
timed-magus: `time` around a silent magus run, which already reports its own durationsAn advisory by default: it explains, and blocks nothing, on `time` around a silent magus run, which already reports its own durations.
tool-boundaryAn advisory by default: it explains, and blocks nothing, on a description that names no case where the tool is the wrong choice and no tool to use instead.
tool-leadAn advisory by default: it explains, and blocks nothing, on a description whose first sentence opens on the tool itself, holds under 4 words or runs past 40 words.
tool-lengthAn advisory by default: it explains, and blocks nothing, on a tool or skill description over 1024 runes.
unbacked-doneAn advisory by default: it explains, and blocks nothing, on a claim of done, fixed, verified or passing with no command, output ref, file or link beside it.
unleased-write: a write magus cannot attribute while a fleet is runningAn advisory by default: it explains, and blocks nothing, on a write magus cannot attribute while a fleet is running.
verdictAn advisory by default: it explains, and blocks nothing, on a judgment word standing in for the behavior it judges ("was broken", "a mess").
voice-driftAn advisory by default: it explains, and blocks nothing, on a draft that reads further from its author's own texts of its kind than 95 percent of them do, or a commit subject longer than 95 percent of the author's.
why-openerAn advisory by default: it explains, and blocks nothing, on a review reply sentence that opens "Why did you" or "Why would you".
wordyAn advisory by default: it explains, and blocks nothing, on a phrase with a shorter equivalent ("in order to").
workspace-command-failed: a command the workspace's rule could not judge, so only the built-in rules graded itAn advisory by default: it explains, and blocks nothing, on a command the workspace's rule could not judge, so only the built-in rules graded it.
workspace-spawn-failed: a spawn the workspace's rule could not judge, so only the built-in rules graded itAn advisory by default: it explains, and blocks nothing, on a spawn the workspace's rule could not judge, so only the built-in rules graded it.
workspace-write-failed: a file write the workspace's rule could not judge, so only the built-in rules graded itAn advisory by default: it explains, and blocks nothing, on a file write the workspace's rule could not judge, so only the built-in rules graded it.