kmshihab7878/claude-code-setup/operating-framework

Claude Code and agent skill by kmshihab7878/claude-code-setup

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Task routing, risk assessment, execution modes, and completion standards for meaningful work.

Install

npx vskill@latest install kmshihab7878/claude-code-setup/operating-framework

SKILL.md

Operating Framework v1.0

Macro-level routing for meaningful work. It classifies lane, risk, mode, required artifacts, evidence, and completion standard. It integrates with existing gates and commands; it does not replace them.

Triggers

Activate on every meaningful task. Trivial tasks such as a single lookup, file read, or quick answer can bypass the full framework, but safety, verification, and approval gates still apply.

Session Contract

For non-trivial work, route before acting:

text
TASK: [one-line description]
LANE: [Explore | Specify | Build | Verify | Ship | Recover]
RISK: [T0 Safe | T1 Local | T2 Shared | T3 Critical]
MODE: [A Founder | B Elite Engineering | C Recovery | D Secure Delivery]
ARTIFACTS: [what this task must produce]
EVIDENCE: [what proves completion]
COUNCIL: [Solo | Lead+Reviewer | Full Council]
DONE WHEN: [measurable completion condition]

Use /start-task when an explicit header is useful; otherwise route mentally before acting.

Lane and Risk Rules

LaneUse ForRequired Standard
ExploreVague request, unknown scope, "what if"Questions, options, or brief before specification
SpecifyBehavior change or new capabilitySpec, acceptance criteria, and plan before build
BuildApproved spec or clear planCode, tests, docs as needed
VerifyExisting work needs validationTest results and review findings
ShipVerified work ready for deliveryCommit/PR/deploy checklist and evidence
RecoverBug, incident, regression, failureRoot cause before fix, then regression check
RiskScopeBehavior
T0 SafeLocal, read-only, reversibleProceed freely
T1 LocalLocal workspace writesExecute narrowly and verify
T2 SharedShared systems, remotes, data, configPause before shared/irreversible action
T3 CriticalProduction, financial, security, secrets, irreversibleFull review and explicit user approval

If unsure, escalate one tier. Production is T2+, financial/trading is T3, and security-sensitive work is T2+.

Operating Modes

ModeWhenTypical Sequence
A FounderGreenfield product or featurebrainstorm -> spec -> architecture -> plan -> build -> verify
B Elite EngineeringApproved spec and clear implementationplan -> test -> build -> review -> document
C RecoveryBug, failure, incident, regressiondebug -> review -> test -> reflect
D Secure DeliverySecurity-sensitive, deployment, infrasecurity audit -> review -> build

See operating-modes.md for detailed mode playbooks.

Decision Tree

  1. Vague or exploratory? Use Explore.
  2. Behavior change or new capability? Use Specify before Build.
  3. Bug, failure, or regression? Use Recover.
  4. Production, money, security, secrets, shared state, or irreversible action? Escalate to T2/T3.
  5. Multiple domains or high-stakes tradeoff? Convene council.
  6. Otherwise use Solo execution with the matching mode.

Enforcement Rules

  • Do not cross lane boundaries without required artifacts.
  • Do not claim completion without evidence.
  • Do not fix bugs before stating root cause with supporting evidence.
  • T2/T3 actions require explicit checkpoint before irreversible or shared action.
  • Every review finding gets a disposition: accepted, deferred with reason, or rejected with reason.

Completion Standard

Every non-trivial task ends with a completion packet or equivalent final report covering:

  • Summary.
  • Changed files and artifacts.
  • Tests or validation run.
  • Evidence.
  • Risks, rollback path, open questions, and next step when applicable.

See completion-and-precedence.md for the full packet template and skill precedence rules.

Escape Hatch

If the user explicitly says "just do it", "skip routing", "emergency mode", or "no framework needed", streamline the framework. Never skip:

  • No fabrication.
  • Security-first behavior.
  • Verify before asserting.
  • Approval gates for T2/T3, destructive, secret-affecting, production, or irreversible actions.

See escape-hatch-and-integrations.md for bypass logging and integration points.

Reference Map

NeedRead
Session contract, lane definitions, risk tiers, decision tree, artifact matrix, enforcement rulesrouting-and-artifacts.md
Operating mode detailoperating-modes.md
Council compositions and decision formatcouncils.md
Memory promotion and benchmark metricsmemory-and-metrics.md
Golden workflowsgolden-workflows.md
Completion packet and skill precedencecompletion-and-precedence.md
Escape hatch and integration pointsescape-hatch-and-integrations.md

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
6
Repository forks
1
7-day trend score
10

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/kmshihab7878/claude-code-setup/operating-framework/badge)](https://verified-skill.com/skills/kmshihab7878/claude-code-setup/operating-framework)

Something wrong with this skill or its page? Tell us.