All Claude Code modsMahadSalim/claude-mods
usage-log
Logs plan readings, context fill, engine cost, turn outcomes, tool timing, permission asks, commands and settings hook runs per session. Records what each session loads into its context and applies the rules set in the dashboard's Context tab: defer or rewrite tools, rewrite or drop the skill listing, injected blocks and system prompt sections, reorder the sections, cap file reads. Serves the usage dashboard at http://127.0.0.1:5198, started with each session; needs node on the PATH. /usage-dashboard turns the server on or off. /usage-dashboard auto turns the start with each session on or off.
usage-log reaches L3 (network) and passed claude plugin validate with warnings on Claude Code 2.1.302.
- Events hooked: 14
- API methods referenced: 15
- Access from classified calls: L3, network: network, runs processes, writes files, reads files, reads env vars, persists state, draws
- Static scan, not a runtime test
Install hint
/plugin install usage-log --marketplace MahadSalim/claude-modsFrom the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later.
Access
L3 Uses the networknetwork, runs processes, writes files, reads files, reads env vars, persists state, drawsValidation
Passed with warnings on Claude Code 2.1.302View the source on GitHub Back to the list
What the scan recorded
- Observed events
- every tool call, every skill, classic hooks, compaction
- Hooks
session.start, command.run, command.run {command=usage-dashboard}, turn.start, turn.complete, session.measure, tool.check, tool.call, tool.describe, prompt.compose, prompt.attachment, skill.prompt, classic.*, session.compact, session.end- API calls
$.clock.now, $.command.register, $.env.get, $.fs.read, $.fs.stat, $.fs.write, $.http.fetch, $.process.run, $.session.id, $.session.model, $.session.usage, $.session.version, $.store.get, $.store.set, $.ui.invalidate- Validation on 2.1.302
- Passed with warnings
- Scanned revision
a98c4fb4e472- Marketplace warnings
- claude-mods
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. How the scan works.
More from MahadSalim/claude-mods
- agent-delegationThe delegation mode, subagent cap and model routing.
- context-barA bar above the prompt that fills as the context window fills.
- prompt-toolsRewrites a typed prompt with Haiku and appends saved text to it.
- turn-rulesSends questions through AskUserQuestion and keeps a turn going while the task list has open tasks.
- ui-modA band button and a pane that draw and change the settings of every other mod.
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/MahadSalim--claude-mods--usage-log/)
[](https://mods.aidojo.si/mods/MahadSalim--claude-mods--usage-log/)