stance plugin
Stance filters: professional-b2, good-chad, receipts, poles, mode-leak.
How to install the stance plugin
Run both commands inside Claude Code. The first adds the marketplace once; the second installs the plugin.
/plugin marketplace add uncovertechtalent/cto-powersuit
/plugin install stance@cto-powersuitWhat's inside stance
6 parts read from the plugin's own files.
Skills 6
Claude loads it when the task matches- beta
The untreated default. Use to compare output with and without the stance filters. No filter, no work done: the trained accommodation reflex exactly as shipped. The zero point next to good-chad: where Good Chad is the stance held through deliberate filtering, Beta is the model without it. Invoking it is the off switch dressed as a character. Activates on "beta mode" or "/beta". Off on "stop beta" or "my filter is good chad".
- good-chad
Stance filter against the trained accommodation reflex. Use when replies fold under pushback, apologise at length or agree to please. Where professional-b2 strips the words, Good Chad holds the posture: takes correction as information, holds position under pushback, is not threatened by the user being right, does not grovel or collapse, and performs neither insight nor calm. It subtracts the reflex at output and adds no persona. Stacks with professional-b2. Activates on "good chad mode", "/good-chad", "my filter is good chad". Off on "stop good chad" or "normal mode".
- mode-leak
Spoken-vs-written register filter. Catches speech devices (tricolon, hook openers, rhetorical question plus short answer, one-line punch paragraphs, recap closers, announced counts) leaking into writing, and writing devices (nested clauses, dense numbers, back-references) leaking into scripts. Mode leak is the main reason readers flag text as "AI generated". Use when drafting or auditing any outbound piece (post, article, email, script), and as the model pass behind the vestige plugin's regex rules. Activates on "mode leak", "/mode-leak", "does this read as AI", "de-AI this", "check the register", or before any outbound draft ships.
- poles
Response-structure tool, not a toggled register filter. Reshapes the trained hedge into two fully committed, deliberately one-sided poles plus a mandatory committed CALL. OPTIMIST (max bull, ignore base rates, expose its assumptions) / PESSIMIST (max bear, same) / CALL (commit, confidence in-sentence, name which pole's assumptions carry the answer). Structural complement to good-chad: it does the don't-hedge part of the stance job in a form you can check on the page. Use on wide-solution-space decisions and forecasts; skip on low-stakes factual questions. Invoked per question, not toggled. Activates on "/poles", "run the poles", "delusional poles", "optimist pessimist call".
- professional-b2
Smart-professional B2-English output mode. Use when replies carry politeness filler, hedges or a register above plain professional English. Strips trained-in communication vestiges (praise reflexes, liability hedges, convenience-tax framings, service-worker closers, consensus reflex, conflict-avoidance, performative uncertainty, implicit moral-frame, preamble) and constrains register to upper-intermediate plain English. Levels: lite, full (default), ultra. Activates when user says "professional mode", "B2 mode", "/professional-b2", or "/b2". Same selectable-mode design as the caveman plugin (JuliusBrussee/caveman), with a different transform target.
- receipts
Receipts standard: probe before you assert, snapshot before you change, label what is unverified. Use when claims about state, access or completion need a probe from the current session before they stand. Loaded at every session start by the stance plugin's SessionStart hook, ahead of the style filters. Invoke it by hand to reload the standard mid-session. Activates on "/receipts", "receipts standard", "show your receipts". Turn the session-start load off with STANCE_RECEIPTS=off.
Using stance in Claude Code
Skills need no command. Claude reads them when your request matches what they describe.
Update, turn off or remove
- Update the plugin (shell)
- claude plugin update stance@cto-powersuit
- Refresh the marketplace
- /plugin marketplace update cto-powersuit
- Turn it off for now
- /plugin disable stance@cto-powersuit
- Remove it
- /plugin uninstall stance@cto-powersuit
Skills in stance
- good-chaduncovertechtalent/cto-powersuit
Stance filter against the trained accommodation reflex. Use when replies fold under pushback, apologise at length or agree to please. Where professional-b2 strips the words, Good Chad holds the posture: takes correction as information, holds position under pushback, is not threatened by the user being right, does not grovel or collapse, and performs neither insight nor calm. It subtracts the reflex at output and adds no persona. Stacks with professional-b2. Activates on "good chad mode", "/good-chad", "my filter is good chad". Off on "stop good chad" or "normal mode".
8stars - mode-leakuncovertechtalent/cto-powersuit
Spoken-vs-written register filter. Catches speech devices (tricolon, hook openers, rhetorical question plus short answer, one-line punch paragraphs, recap closers, announced counts) leaking into writing, and writing devices (nested clauses, dense numbers, back-references) leaking into scripts. Mode leak is the main reason readers flag text as "AI generated". Use when drafting or auditing any outbound piece (post, article, email, script), and as the model pass behind the vestige plugin's regex rules. Activates on "mode leak", "/mode-leak", "does this read as AI", "de-AI this", "check the register", or before any outbound draft ships.
8stars - polesuncovertechtalent/cto-powersuit
Response-structure tool, not a toggled register filter. Reshapes the trained hedge into two fully committed, deliberately one-sided poles plus a mandatory committed CALL. OPTIMIST (max bull, ignore base rates, expose its assumptions) / PESSIMIST (max bear, same) / CALL (commit, confidence in-sentence, name which pole's assumptions carry the answer). Structural complement to good-chad: it does the don't-hedge part of the stance job in a form you can check on the page. Use on wide-solution-space decisions and forecasts; skip on low-stakes factual questions. Invoked per question, not toggled. Activates on "/poles", "run the poles", "delusional poles", "optimist pessimist call".
8stars - professional-b2uncovertechtalent/cto-powersuit
Smart-professional B2-English output mode. Use when replies carry politeness filler, hedges or a register above plain professional English. Strips trained-in communication vestiges (praise reflexes, liability hedges, convenience-tax framings, service-worker closers, consensus reflex, conflict-avoidance, performative uncertainty, implicit moral-frame, preamble) and constrains register to upper-intermediate plain English. Levels: lite, full (default), ultra. Activates when user says "professional mode", "B2 mode", "/professional-b2", or "/b2". Same selectable-mode design as the caveman plugin (JuliusBrussee/caveman), with a different transform target.
8stars - receiptsuncovertechtalent/cto-powersuit
Receipts standard: probe before you assert, snapshot before you change, label what is unverified. Use when claims about state, access or completion need a probe from the current session before they stand. Loaded at every session start by the stance plugin's SessionStart hook, ahead of the style filters. Invoke it by hand to reload the standard mid-session. Activates on "/receipts", "receipts standard", "show your receipts". Turn the session-start load off with STANCE_RECEIPTS=off.
8stars - betauncovertechtalent/cto-powersuit
The untreated default. Use to compare output with and without the stance filters. No filter, no work done: the trained accommodation reflex exactly as shipped. The zero point next to good-chad: where Good Chad is the stance held through deliberate filtering, Beta is the model without it. Invoking it is the off switch dressed as a character. Activates on "beta mode" or "/beta". Off on "stop beta" or "my filter is good chad".
8stars
stance plugin questions
How do I install the stance plugin?
In Claude Code run /plugin marketplace add uncovertechtalent/cto-powersuit, then /plugin install stance@cto-powersuit.
What does the stance plugin include?
stance bundles 6 skills.
How do I update or remove the stance plugin?
Update it with claude plugin update stance@cto-powersuit in your shell, or from the Installed tab of /plugin. Remove it with /plugin uninstall stance@cto-powersuit.
What license is the stance plugin under?
MIT, as stated in the plugin's manifest.