[codex] add skill context budget guardrails

SKILL.md

@@ -3,10 +3,7 @@ name: gstack
 preamble-tier: 1
 version: 1.1.0
 description: |
-  Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with
-  elements, verify state, diff before/after, take annotated screenshots, test responsive
-  layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or
-  test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
+  gstack browser workflow for opening, testing, and dogfooding web pages with screenshots and evidence.
 allowed-tools:
   - Bash
   - Read

SKILL.md.tmpl

@@ -3,10 +3,7 @@ name: gstack
 preamble-tier: 1
 version: 1.1.0
 description: |
-  Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with
-  elements, verify state, diff before/after, take annotated screenshots, test responsive
-  layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or
-  test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
+  gstack browser workflow for opening, testing, and dogfooding web pages with screenshots and evidence.
 allowed-tools:
   - Bash
   - Read

autoplan/SKILL.md

@@ -3,14 +3,7 @@ name: autoplan
 preamble-tier: 3
 version: 1.0.0
 description: |
-  Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk
-  and runs them sequentially with auto-decisions using 6 decision principles. Surfaces
-  taste decisions (close approaches, borderline scope, codex disagreements) at a final
-  approval gate. One command, fully reviewed plan out.
-  Use when asked to "auto review", "autoplan", "run all reviews", "review this plan
-  automatically", or "make the decisions for me".
-  Proactively suggest when the user has a plan file and wants to run the full review
-  gauntlet without answering 15-30 intermediate questions. (gstack)
+  gstack auto-review pipeline that runs CEO, eng, design, and DX reviews with final taste decisions.
   Voice triggers (speech-to-text aliases): "auto plan", "automatic review".
 benefits-from: [office-hours]
 triggers:

autoplan/SKILL.md.tmpl

@@ -3,14 +3,7 @@ name: autoplan
 preamble-tier: 3
 version: 1.0.0
 description: |
-  Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk
-  and runs them sequentially with auto-decisions using 6 decision principles. Surfaces
-  taste decisions (close approaches, borderline scope, codex disagreements) at a final
-  approval gate. One command, fully reviewed plan out.
-  Use when asked to "auto review", "autoplan", "run all reviews", "review this plan
-  automatically", or "make the decisions for me".
-  Proactively suggest when the user has a plan file and wants to run the full review
-  gauntlet without answering 15-30 intermediate questions. (gstack)
+  gstack auto-review pipeline that runs CEO, eng, design, and DX reviews with final taste decisions.
 voice-triggers:
   - "auto plan"
   - "automatic review"

benchmark-models/SKILL.md

@@ -3,12 +3,7 @@ name: benchmark-models
 preamble-tier: 1
 version: 1.0.0
 description: |
-  Cross-model benchmark for gstack skills. Runs the same prompt through Claude,
-  GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost,
-  and optionally quality via LLM judge. Answers "which model is actually best
-  for this skill?" with data instead of vibes. Separate from /benchmark, which
-  measures web page performance. Use when: "benchmark models", "compare models",
-  "which model is best for X", "cross-model comparison", "model shootout". (gstack)
+  gstack model benchmark for comparing Claude, GPT, and Gemini on a skill or prompt.
   Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".
 triggers:
   - cross model benchmark

benchmark-models/SKILL.md.tmpl

@@ -3,12 +3,7 @@ name: benchmark-models
 preamble-tier: 1
 version: 1.0.0
 description: |
-  Cross-model benchmark for gstack skills. Runs the same prompt through Claude,
-  GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost,
-  and optionally quality via LLM judge. Answers "which model is actually best
-  for this skill?" with data instead of vibes. Separate from /benchmark, which
-  measures web page performance. Use when: "benchmark models", "compare models",
-  "which model is best for X", "cross-model comparison", "model shootout". (gstack)
+  gstack model benchmark for comparing Claude, GPT, and Gemini on a skill or prompt.
 voice-triggers:
   - "compare models"
   - "model shootout"

benchmark/SKILL.md

@@ -3,11 +3,7 @@ name: benchmark
 preamble-tier: 1
 version: 1.0.0
 description: |
-  Performance regression detection using the browse daemon. Establishes
-  baselines for page load times, Core Web Vitals, and resource sizes.
-  Compares before/after on every PR. Tracks performance trends over time.
-  Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals",
-  "bundle size", "load time". (gstack)
+  gstack performance benchmark for page load, Core Web Vitals, bundle size, and regression baselines.
   Voice triggers (speech-to-text aliases): "speed test", "check performance".
 triggers:
   - performance benchmark

benchmark/SKILL.md.tmpl

@@ -3,11 +3,7 @@ name: benchmark
 preamble-tier: 1
 version: 1.0.0
 description: |
-  Performance regression detection using the browse daemon. Establishes
-  baselines for page load times, Core Web Vitals, and resource sizes.
-  Compares before/after on every PR. Tracks performance trends over time.
-  Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals",
-  "bundle size", "load time". (gstack)
+  gstack performance benchmark for page load, Core Web Vitals, bundle size, and regression baselines.
 voice-triggers:
   - "speed test"
   - "check performance"

browse/SKILL.md

@@ -3,12 +3,7 @@ name: browse
 preamble-tier: 1
 version: 1.1.0
 description: |
-  Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with
-  elements, verify page state, diff before/after actions, take annotated screenshots, check
-  responsive layouts, test forms and uploads, handle dialogs, and assert element states.
-  ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a
-  user flow, or file a bug with evidence. Use when asked to "open in browser", "test the
-  site", "take a screenshot", or "dogfood this". (gstack)
+  gstack headless browser for navigating pages, clicking UI, checking state, and capturing screenshots.
 triggers:
   - browse a page
   - headless browser

browse/SKILL.md.tmpl

@@ -3,12 +3,7 @@ name: browse
 preamble-tier: 1
 version: 1.1.0
 description: |
-  Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with
-  elements, verify page state, diff before/after actions, take annotated screenshots, check
-  responsive layouts, test forms and uploads, handle dialogs, and assert element states.
-  ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a
-  user flow, or file a bug with evidence. Use when asked to "open in browser", "test the
-  site", "take a screenshot", or "dogfood this". (gstack)
+  gstack headless browser for navigating pages, clicking UI, checking state, and capturing screenshots.
 triggers:
   - browse a page
   - headless browser

canary/SKILL.md

@@ -3,11 +3,7 @@ name: canary
 preamble-tier: 2
 version: 1.0.0
 description: |
-  Post-deploy canary monitoring. Watches the live app for console errors,
-  performance regressions, and page failures using the browse daemon. Takes
-  periodic screenshots, compares against pre-deploy baselines, and alerts
-  on anomalies. Use when: "monitor deploy", "canary", "post-deploy check",
-  "watch production", "verify deploy". (gstack)
+  gstack post-deploy canary monitor for production page failures, console errors, and performance regressions.
 allowed-tools:
   - Bash
   - Read

canary/SKILL.md.tmpl

@@ -3,11 +3,7 @@ name: canary
 preamble-tier: 2
 version: 1.0.0
 description: |
-  Post-deploy canary monitoring. Watches the live app for console errors,
-  performance regressions, and page failures using the browse daemon. Takes
-  periodic screenshots, compares against pre-deploy baselines, and alerts
-  on anomalies. Use when: "monitor deploy", "canary", "post-deploy check",
-  "watch production", "verify deploy". (gstack)
+  gstack post-deploy canary monitor for production page failures, console errors, and performance regressions.
 allowed-tools:
   - Bash
   - Read

careful/SKILL.md

@@ -2,11 +2,7 @@
 name: careful
 version: 0.1.0
 description: |
-  Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE,
-  force-push, git reset --hard, kubectl delete, and similar destructive operations.
-  User can override each warning. Use when touching prod, debugging live systems,
-  or working in a shared environment. Use when asked to "be careful", "safety mode",
-  "prod mode", or "careful mode". (gstack)
+  gstack safety guardrails that warn before destructive shell commands in risky environments.
 triggers:
   - be careful
   - warn before destructive

careful/SKILL.md.tmpl

@@ -2,11 +2,7 @@
 name: careful
 version: 0.1.0
 description: |
-  Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE,
-  force-push, git reset --hard, kubectl delete, and similar destructive operations.
-  User can override each warning. Use when touching prod, debugging live systems,
-  or working in a shared environment. Use when asked to "be careful", "safety mode",
-  "prod mode", or "careful mode". (gstack)
+  gstack safety guardrails that warn before destructive shell commands in risky environments.
 triggers:
   - be careful
   - warn before destructive

claude/SKILL.md.tmpl

@@ -3,11 +3,7 @@ name: claude
 preamble-tier: 3
 version: 1.0.0
 description: |
-  Claude Code CLI wrapper for non-Claude hosts - three modes. Review: independent
-  diff review via claude -p. Challenge: adversarial failure-mode review. Consult:
-  ask Claude about the repo with read-only file tools. Use when asked for "claude
-  review", "claude challenge", "ask claude", "second opinion from claude", or
-  "outside voice". (gstack)
+  gstack Claude CLI wrapper for review, challenge, and read-only consultation from non-Claude hosts.
 triggers:
   - claude review
   - claude challenge

codex/SKILL.md

@@ -3,11 +3,7 @@ name: codex
 preamble-tier: 3
 version: 1.0.0
 description: |
-  OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via
-  codex review with pass/fail gate. Challenge: adversarial mode that tries to break
-  your code. Consult: ask codex anything with session continuity for follow-ups.
-  The "200 IQ autistic developer" second opinion. Use when asked to "codex review",
-  "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack)
+  gstack Codex CLI wrapper for review, adversarial challenge, and session-continuity consultation.
   Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".
 triggers:
   - codex review

codex/SKILL.md.tmpl

@@ -3,11 +3,7 @@ name: codex
 preamble-tier: 3
 version: 1.0.0
 description: |
-  OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via
-  codex review with pass/fail gate. Challenge: adversarial mode that tries to break
-  your code. Consult: ask codex anything with session continuity for follow-ups.
-  The "200 IQ autistic developer" second opinion. Use when asked to "codex review",
-  "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack)
+  gstack Codex CLI wrapper for review, adversarial challenge, and session-continuity consultation.
 voice-triggers:
   - "code x"
   - "code ex"

context-restore/SKILL.md

@@ -3,13 +3,7 @@ name: context-restore
 preamble-tier: 2
 version: 1.0.0
 description: |
-  Restore working context saved earlier by /context-save. Loads the most recent
-  saved state (across all branches by default) so you can pick up where you
-  left off — even across Conductor workspace handoffs.
-  Use when asked to "resume", "restore context", "where was I", or
-  "pick up where I left off". Pair with /context-save.
-  Formerly /checkpoint resume — renamed because Claude Code treats /checkpoint
-  as a native rewind alias in current environments. (gstack)
+  gstack context restore loads saved session state so work can resume across branches or workspaces.
 allowed-tools:
   - Bash
   - Read

context-restore/SKILL.md.tmpl

@@ -3,13 +3,7 @@ name: context-restore
 preamble-tier: 2
 version: 1.0.0
 description: |
-  Restore working context saved earlier by /context-save. Loads the most recent
-  saved state (across all branches by default) so you can pick up where you
-  left off — even across Conductor workspace handoffs.
-  Use when asked to "resume", "restore context", "where was I", or
-  "pick up where I left off". Pair with /context-save.
-  Formerly /checkpoint resume — renamed because Claude Code treats /checkpoint
-  as a native rewind alias in current environments. (gstack)
+  gstack context restore loads saved session state so work can resume across branches or workspaces.
 allowed-tools:
   - Bash
   - Read

context-save/SKILL.md

@@ -3,13 +3,7 @@ name: context-save
 preamble-tier: 2
 version: 1.0.0
 description: |
-  Save working context. Captures git state, decisions made, and remaining work
-  so any future session can pick up without losing a beat.
-  Use when asked to "save progress", "save state", "context save", or
-  "save my work". Pair with /context-restore to resume later.
-  Formerly /checkpoint — renamed because Claude Code treats /checkpoint as a
-  native rewind alias in current environments, which was shadowing this skill.
-  (gstack)
+  gstack context save records git state, decisions, and remaining work for later resume.
 allowed-tools:
   - Bash
   - Read

context-save/SKILL.md.tmpl

@@ -3,13 +3,7 @@ name: context-save
 preamble-tier: 2
 version: 1.0.0
 description: |
-  Save working context. Captures git state, decisions made, and remaining work
-  so any future session can pick up without losing a beat.
-  Use when asked to "save progress", "save state", "context save", or
-  "save my work". Pair with /context-restore to resume later.
-  Formerly /checkpoint — renamed because Claude Code treats /checkpoint as a
-  native rewind alias in current environments, which was shadowing this skill.
-  (gstack)
+  gstack context save records git state, decisions, and remaining work for later resume.
 allowed-tools:
   - Bash
   - Read

cso/SKILL.md

@@ -3,12 +3,7 @@ name: cso
 preamble-tier: 2
 version: 2.0.0
 description: |
-  Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology,
-  dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain
-  scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification.
-  Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep
-  scan, 2/10 bar). Trend tracking across audit runs.
-  Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review". (gstack)
+  gstack security audit for secrets, dependencies, CI/CD, LLM risks, OWASP, and threat modeling.
   Voice triggers (speech-to-text aliases): "see-so", "see so", "security review", "security check", "vulnerability scan", "run security".
 allowed-tools:
   - Bash

cso/SKILL.md.tmpl

@@ -3,12 +3,7 @@ name: cso
 preamble-tier: 2
 version: 2.0.0
 description: |
-  Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology,
-  dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain
-  scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification.
-  Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep
-  scan, 2/10 bar). Trend tracking across audit runs.
-  Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review". (gstack)
+  gstack security audit for secrets, dependencies, CI/CD, LLM risks, OWASP, and threat modeling.
 voice-triggers:
   - "see-so"
   - "see so"

design-consultation/SKILL.md

@@ -3,13 +3,7 @@ name: design-consultation
 preamble-tier: 3
 version: 1.0.0
 description: |
-  Design consultation: understands your product, researches the landscape, proposes a
-  complete design system (aesthetic, typography, color, layout, spacing, motion), and
-  generates font+color preview pages. Creates DESIGN.md as your project's design source
-  of truth. For existing sites, use /plan-design-review to infer the system instead.
-  Use when asked to "design system", "brand guidelines", or "create DESIGN.md".
-  Proactively suggest when starting a new project's UI with no existing
-  design system or DESIGN.md. (gstack)
+  gstack design consultation for creating a product design system and DESIGN.md source of truth.
 allowed-tools:
   - Bash
   - Read

design-consultation/SKILL.md.tmpl

@@ -3,13 +3,7 @@ name: design-consultation
 preamble-tier: 3
 version: 1.0.0
 description: |
-  Design consultation: understands your product, researches the landscape, proposes a
-  complete design system (aesthetic, typography, color, layout, spacing, motion), and
-  generates font+color preview pages. Creates DESIGN.md as your project's design source
-  of truth. For existing sites, use /plan-design-review to infer the system instead.
-  Use when asked to "design system", "brand guidelines", or "create DESIGN.md".
-  Proactively suggest when starting a new project's UI with no existing
-  design system or DESIGN.md. (gstack)
+  gstack design consultation for creating a product design system and DESIGN.md source of truth.
 allowed-tools:
   - Bash
   - Read

design-html/SKILL.md

@@ -3,14 +3,7 @@ name: design-html
 preamble-tier: 2
 version: 1.0.0
 description: |
-  Design finalization: generates production-quality Pretext-native HTML/CSS.
-  Works with approved mockups from /design-shotgun, CEO plans from /plan-ceo-review,
-  design review context from /plan-design-review, or from scratch with a user
-  description. Text actually reflows, heights are computed, layouts are dynamic.
-  30KB overhead, zero deps. Smart API routing: picks the right Pretext patterns
-  for each design type. Use when: "finalize this design", "turn this into HTML",
-  "build me a page", "implement this design", or after any planning skill.
-  Proactively suggest when user has approved a design or has a plan ready. (gstack)
+  gstack design-html turns approved designs or plans into production-quality Pretext-native HTML/CSS.
   Voice triggers (speech-to-text aliases): "build the design", "code the mockup", "make it real".
 triggers:
   - build the design

design-html/SKILL.md.tmpl

@@ -3,14 +3,7 @@ name: design-html
 preamble-tier: 2
 version: 1.0.0
 description: |
-  Design finalization: generates production-quality Pretext-native HTML/CSS.
-  Works with approved mockups from /design-shotgun, CEO plans from /plan-ceo-review,
-  design review context from /plan-design-review, or from scratch with a user
-  description. Text actually reflows, heights are computed, layouts are dynamic.
-  30KB overhead, zero deps. Smart API routing: picks the right Pretext patterns
-  for each design type. Use when: "finalize this design", "turn this into HTML",
-  "build me a page", "implement this design", or after any planning skill.
-  Proactively suggest when user has approved a design or has a plan ready. (gstack)
+  gstack design-html turns approved designs or plans into production-quality Pretext-native HTML/CSS.
 voice-triggers:
   - "build the design"
   - "code the mockup"

design-review/SKILL.md

@@ -3,13 +3,7 @@ name: design-review
 preamble-tier: 4
 version: 2.0.0
 description: |
-  Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems,
-  AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues
-  in source code, committing each fix atomically and re-verifying with before/after
-  screenshots. For plan-mode design review (before implementation), use /plan-design-review.
-  Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish".
-  Proactively suggest when the user mentions visual inconsistencies or
-  wants to polish the look of a live site. (gstack)
+  gstack live design audit that finds visual issues, fixes code, and verifies with screenshots.
 allowed-tools:
   - Bash
   - Read