reflect 0.1.0
Reflect: /reflect gives a short plain-English retrospective of the session so far (what got done, what went wrong or was redone, what to do differently).
Install
/plugin marketplace add rhetoricnimbus-hub/claude-mods /plugin install reflect@claude-mods
Run both lines inside Claude Code.
Hooks into
- Slash commands
Also in rhetoricnimbus-hub/claude-mods
- subagent-disco 0.1.0 Every running subagent gets a little dancer above the prompt: it busts a move on each tool call and takes a bow when it finishes. 0
- savvy-progress 0.1.0 A live row above the prompt while a turn runs: elapsed time, tool calls so far, and the current step. 0
- skins 0.1.0 Skins: five complete colour themes for the Claude app, switched with /skin <name>. Remembered across sessions; /skin off returns to the default look. 0
- you-should-know 0.1.0 A short toast when something worth knowing happens quietly: a command fails, a file is written outside the working folder, a tool call is refused, or a turn ends on an error. 0
- filetree 0.1.0 A side pane (/filetree) showing every file read, edited or written this session as a folder tree. 0
- cache-tax 0.1.0 Cache Tax: a status line after each turn showing prompt-cache hit rate, tokens read/written and session cost, plus /cachetax for a session breakdown. 0
- blast-radius 0.1.0 Risk-tags risky commands on their tool rows (HIGH or MEDIUM blast radius) and asks for confirmation before a HIGH one runs. 0
- terminal-browser 0.1.0 A side pane (/links) listing every web page fetched, searched or opened this session, newest first. 0
- replay-theater 0.1.0 Replay Theater: a side pane (/replay) that steps through this session's tool calls like a film strip, with Prev/Next/First/Latest and auto-play. 0
More commands mods
- ruflo-arena 0.2.7 Competitive ruliology for Ruflo swarms — arenas, tournaments, and adaptive co-evolution of program strategies (ADR-147/148). Strategies-as-programs compete under payoff games; tournaments produce Wolfram-style competitive arrays; hill-climb and mutual co-evolution discover winners empirically. 82k
- subagent-models 0.1.0 Pins subagent models to a model-routing policy (Opus for judgement, Haiku for mechanical work, Sonnet otherwise) and logs every spawn. 99
- fable-pin 0.1.0 Pins every subagent to the fable model: rewrites the model on agent.spawn unless the spawn is a fork, with /fable-pin on, off and status. Touches nothing but its own store. Needs function hooks (early access). 49
- display-redaction 0.1.17 A mod that masks email addresses and secret-shaped text in what Claude Code draws, for recordings and screen shares. It changes the screen only; the transcript, the model's context and the files on disk are untouched, so it is not a privacy or data control. 32
- nudge 0.1.0 /nudge <goal> applies behavioral design to a product or flow: diagnose why users don't act, design interventions that remove barriers, ranked hypotheses to test, and an ethics check on every answer. Its guide reaches Claude only when you run /nudge. 14