effort-auto 0.3.0
Adaptive thinking effort for the main conversation only: rest at low, raise it by steps when judgement is needed.
yadazInstall
/plugin marketplace add wdsewdser-bit/claude-code-mods /plugin install effort-auto@claude-code-mods
Run both lines inside Claude Code.
Hooks into
- Tool calls
- Model tools
Also in wdsewdser-bit/claude-code-mods
-
cache-keeper
0.5.0
Observes prompt-cache usage, keeps the session's and its finished subagents' caches warm, and runs 5m/1h TTL A/B experiments.
yadaz in Prompt, updated
7
-
ctx-mod
0.2.0
Proactive context management: a task ledger, a searchable history and zero-summary window switches.
yadaz in Prompt, updated
7
-
away-autopilot
0.2.0
用户离开 5 分钟未回复待确认的问题时，提示模型自行决定；模型可调用工具暂停自动推进。
wdsewdser-bit in Prompt, updated
6
-
cc-restart
0.1.0
让会话里的模型自己重启 Claude 桌面版，并在重启后唤醒同一个会话继续干活。
yadaz in Guardrails, updated
6
-
delegate
0.1.0
Hand a task to a cheaper model (any OpenAI chat-protocol provider) through a local Anthropic-to-OpenAI proxy; /delegate manages providers, keys and models.
yadaz in Panes, updated
3
-
dispatch-gate
0.1.0
A soft gate on the main session: reminds it, then refuses once per stretch, to hand work to a subagent; and refuses one Claude subagent per hour past three.
yadaz in Prompt, updated
3
-
ptc-run
0.1.0
Programmatic tool calling: run_code runs a JS program that calls read/glob/grep/edit/bash in a sandbox and returns only the final value; large results spill to refs.
yadaz in Guardrails, updated
3
-
read-dedup
0.1.0
Re-reading a file already in the context returns a one-line notice if unchanged, or only a diff if changed, saving context tokens.
yadaz in Guardrails, updated
3
More guardrails mods
-
blast-radius
0.1.0
See what a risky command would change before it runs.
deepseek-ai in Guardrails, updated
279.9k
-
agents-md
0.1.0
AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working director...
Anthropic in Guardrails, updated
155.5k
-
claude-mem
15.12.1
mod + skill
Persistent memory for AI coding agents: the next session starts where the last one left off. Works with Claude Code, Codex, Cursor, OpenCode and more.
Alex Newman in Guardrails, updated
114.9k
-
ruflo-rvf
0.3.7
mod + skill
RVF format for portable agent memory, session persistence, and cross-platform transfer. As a mod (ADR-445): a write guard that keeps secrets out of memory, sessions and transfers, /rvf-mod, and a status file the console shows
ruvnet in Guardrails, updated
81.6k
-
openviking-memory
0.7.22
mod + skill
Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations.
OpenViking in Guardrails, updated
42.1k