model-pin 0.1.0
Pin a project to one model, show a drift badge when the session leaves it, and re-apply the pin once.
Install
/plugin marketplace add Joseph-Ayoub/claude-mods /plugin install model-pin@joseph-mods
Run both lines inside Claude Code.
Hooks into
- Status line
- Toasts
- Slash commands
Also in Joseph-Ayoub/claude-mods
- rd-ledger 0.2.0 Contemporaneous R&D time and AI-usage ledger: engagement hours by business component, list-price usage estimates, a weekly review with buttons, a CPA export, an optional bridge to rd-tracker, and a live Usage pane (cost, context, rate limits, models, subagents, code changes) behind one footer chi... 0
- merge-lane 0.1.0 One merge lane per repo across concurrent sessions: a priority queue, a Bash merge gate, auto-release on merge, and a wake-up for the next session. 0
- cockpit 0.2.0 One band above the prompt: quick replies, branch/PR/CI standing, decision cards, waiting-on-you items, standing-rule capture and a Hand off chip at natural breaks. 0
- stall-watch 0.1.0 Auto-retries transient API failures (capped), pins a usage-limit countdown, and can resume after a limit reset (opt-in via /stall-watch). 0
- wrap 0.1.1 /wrap close-out command: deterministic git/gh/CI/worktree checklist where unknown is never green. 0
- secret-guard 0.1.0 Holds a prompt that carries a credential shape and offers to send it redacted, telling Claude where the value really lives. 0
- mem-gauge 0.3.1 A pressable memory gauge under the composer and a /mem pane: what is using this Mac's RAM across Claude sessions, agents, models and apps, with rule-based advice. 0
- handoff 0.1.0 /handoff: a handoff note written from this session (secret shapes redacted) under ~/.claude/handoffs/, the conversation cleared, the next prompt pre-filled to continue from the note. What mem-gauge's Hand off button and the cockpit chip run. 0
- usage-gauge 0.1.4 (superseded by rd-ledger) A live cost chip in the prompt footer and a /spend Usage pane: the session's cost, context by category, rate limits, tokens and cache hit per model, subagent share and code changes, without /usage landing in the transcript. 0
More status line mods
- jev-auto-mode 0.1.0 A permission layer driven by a JSON policy: allow, ask or deny every tool call (Bash, edits, web, MCP, subagents, skills), every slash command or skill you type, and every skill preloaded into a subagent. Rules decide first (deny > ask > allow, compound Bash commands split); what no rule covers c... 32.6k
- secrets-veil 0.0.6 Masks secret values in tool results before the model reads them: named vendor variables, value-shape patterns, and high-entropy tokens. No reveal path. 292
- cache-clock 0.1.0 A prompt-cache line under your status line: minutes left while warm, and how many tokens the next message re-caches once cold. /cache-clock setup adds it. 195
- sprint-status 0.1.0 Status line for AILANG sprint work: the most recently touched in-progress sprint under .ailang/state/sprints, its milestones passed and the next one. 35
- glowup 1.0.1 mod + skill A glow-up for Claude Code: a cockpit pane for changes, subagents and context, an activity band, and shareable themes. 23