melodic-software
@melodic-software Organization
Public Skills
Do your research
by melodic-software
"Re-anchor research discipline; audit and correct the work and pending recommendations. Use when: 'do your research', 'you're guessing', 'cite that', 'stop assuming', 'evidence, not vibes', 'you skipped verification', 'that's training-data recall', 'research this properly', 'fact-check that', 'make sure that's right', 'go research and update your recommendations', 'are these recommendations grounded', 're-check what you recommended', or at conversation start. All claims: do-your-research-deep."
claude-code-plugins
by melodic-software
"Audit local CLAUDE.md, AGENTS.md, rules, skills, agents, hook text for instructions current models no longer need, misstated Claude Code behavior, and cross-surface conflicts. Report-only. Use when: 'audit instructions', 'instruction audit', 'are my instructions holding the model back', 'too prescriptive', 'stale Claude Code behavior', 'my @path import is not loading', 'instruction re-reads CLAUDE.md', 'conflicting instructions', 'which instruction wins'. Missing text: audit-prompting-postures."
claude-code-plugins
by melodic-software
"Measure this machine's Claude Code startup context per item, including per-tool attribution /context reports as lump sums, plus a before/after ledger. Use when: 'what is eating my context window at startup', 'measure my startup payload', 'which built-in tools cost the most', 'what would denying this tool save', 'context budget audit', 'baseline my context before trimming', 'did that settings change actually save tokens'. Read-only by default; fix applies one project-scope trim behind approval."
claude-code-plugins
by melodic-software
"Read and report on locally captured Claude Code telemetry, OTEL DuckDB store, collector, optional Aspire dashboard, the per-session hook event log and hook-event JSONL, ccusage, with cross-session trend reports, a per-session report, and store pruning. Use when: 'claude observability', 'OTEL', 'collector', 'token burn rate', 'hook latency', 'cost breakdown', 'how am I doing', 'what did this session do', 'hook event log', 'which hooks fired'; read-only except the explicit clean action."
claude-code-plugins
by melodic-software
"Draft a paste-ready autoMode classifier block by interviewing the user about what should and should not be auto-approved, each entry in the shape the classifier reads well and every section keeping $defaults. Use when: 'help me write auto mode rules', 'draft an autoMode block', 'set up auto mode', 'add an auto-mode rule for X', 'my auto mode rules are too vague', 'rewrite this classifier entry', or an audit shows rules dropped or ignored. Prints only, never writes a settings file."
claude-code-plugins
by melodic-software
"Report the Claude Code permission state in effect: merges every settings scope into the effective allow/ask/deny set, each rule with its source and precedence, and flags allow rules auto mode drops. Report-only. Use when: 'what permissions are actually in effect', 'show me my effective permissions', 'which of my rules survive auto mode', 'is my managed policy being read', or before changing a rule whose source is unknown. A rule ignored for its shape: audit-permission-grants."
Claude Code inventory — <host>, <date>
by melodic-software
"List every Claude Code surface this machine can invoke: built-in commands, bundled skills and workflows, and installed plugin components. Use when: 'what slash commands do I have', 'list all my skills', 'what agents are available', 'show me every plugin component', 'what does Claude Code ship built-in', 'is /foo a real command', 'is /foo documented', 'what changed after the update', 'show me only the plugin ones', 'what does marketplace X give me'. On-disk audit: /claude-ops:audit-install-state."
Candidates: merge the extraction, the repo tree, and the seeded pairs.
by melodic-software
"Find where this repo's skills and agents duplicate a native Claude Code surface. Read-only unless apply bakes an approved reference. Enumerating what is invocable: /claude-ops:inventory. Use when: 'does this skill duplicate a built-in', 'what does Claude Code already ship for this', 'audit native overlap', 'is our install-state audit the same as /doctor', 'refresh the native-surfaces registry', 'bake the native reference into this skill', 'which of our skills overlap bundled skills'."
claude-code-plugins
by melodic-software
"When the built-in skill-doctor command resolves in this session, prefer it for cost; this skill for unseen ones. Use when: 'why do I never use most of my skills', 'why does Claude never suggest this skill', 'are my skill descriptions being dropped', 'is my skill listing over budget', 'which skills can the model actually see', 'which skills are starved', 'I have too many skills to know when to use them', 'audit skill visibility'."
claude-code-plugins
by melodic-software
"Measure lines per file for the changed files (the default), explicit paths, or the whole tree (--all), every text file in every lane, each beside a configurable reference with its provenance, longest first. Reports, never gates. Use when: 'how long are these files', 'lines per file', 'file size audit', 'which files are too big', 'LOC per file', 'is this file over 1000 lines', 'count lines in the change'. Complexity: /code-metrics:audit-complexity."
claude-code-plugins
by melodic-software
"Read coverage artifacts a build already wrote (lcov, Cobertura, coverage.py JSON, a Go cover profile) and report line coverage per file and function, plus CRAP per function, for a change, a path, or the tree. Runs no tests, never gates. Use when: 'coverage of this change', 'coverage per function', 'CRAP score', 'which functions are complex and untested', 'read the lcov report', 'coverage.xml', 'how covered is this file'. Complexity alone: /code-metrics:audit-complexity."
claude-code-plugins
by melodic-software
"Verify claude-ops's personal path configuration for this repository (where the known-issues registry, the skill-usage log and the per-session hook event log resolve), check the self-ignoring guard on the hook log root, check that node resolves for the hook launcher, detect retired conventions, and explain how to change the options through Claude Code. Use when: 'set up claude-ops', 'configure claude-ops', 'claude-ops setup', 'where does the known-issues registry live', 'where is skill usage logged', 'set up hook logging', 'where does the hook event log live', or 'turn on session event logging'. check (read-only, default) verifies and reports; apply writes exactly one file, the guard inside the hook log root, and runs the gated retired-convention cleanup. Every option itself is reconfigured through Claude Code, never by this skill. Re-runnable and safe."
claude-code-plugins
by melodic-software
"Ingest Claude Code changelog entries and integrate them into the current repo. Fetch (read-only display), diff (impact analysis over a release range, no edits), status (read marker, default range, replay cap), and apply (full integrate pipeline, explicit user intent only). Use when: 'new cc version', 'what changed in claude code', 'apply changelog', a new CC release is mentioned, or the user pastes changelog text."
claude-code-plugins
by melodic-software
"Classify code comments for residue: history narration, plan/session references, conversational antecedents, ticket/PR back-references, and origin notes. Read-only. Use when: 'comment residue', 'audit code comments', 'find stale/narrative comments', 'strip conversational comments', 'origin note', or before committing agent-written code. Not for removing ALL comments, restating-the-code redundancy (/code-tidying:tidy), or markdown noise (/docs-hygiene:audit-noise)."
Committed on branch (vs merge base) + uncommitted working tree changes
by melodic-software
"When the bundled simplify skill resolves in this session, prefer it for single-file cleanup; this skill for batch sweeps. Batch-run simplification across changed files or a whole repository, grouped by ecosystem and dependency order. Use when: 'batch simplify', 'simplify recent changes', 'forgot to run simplify', 'catch up on simplify', sweeping a branch, repo, or directory, or after a multi-session sprint. Skip for single-file cleanup. Use /simplify instead."
Step 1: name → Context7 library ID
by melodic-software
"Look up current library documentation, API references, and code examples via Context7 (ctx7 CLI or the Context7 MCP server, same backend). Use when: 'look up the docs for X', 'how do I migrate to X v2', or whenever a question names a library, framework, SDK, CLI tool, or cloud service, including API syntax, configuration, setup, and version-migration questions. Actions: lookup <library> <query> (default) update (CLI upgrade + upstream drift check). For CLI/MCP setup, auth, and Windows gotchas, run /context7:setup."
claude-code-plugins
by melodic-software
"Bare-baseline experiment: reversibly strip a repo's standing instructions on a dedicated branch, log stumbles against the bare model, then restore only instructions with repeated same-cause evidence. Measures the model where audit-instructions judges the text. Use when: 'unhobble', 'run the bare experiment', 'delete my CLAUDE.md and see', 'does the model still need these instructions', 'new model dropped, re-baseline', 'instruction ablation experiment', 'deletion watch', 'watch this rule before deleting it'. Human-gated, resumable."
claude-code-plugins
by melodic-software
"Start, restart, stop, and check loop lanes as named background Claude Code sessions seeded from canonical prompt files, the scripted replacement for the manual morning refresh (cancel loop, clear, re-paste the canonical prompt) across N lanes on a machine. start/restart first pull the repo and refresh the plugin marketplace, then launch each configured lane with its per-lane model/effort. consume-restarts reads each configured lane's telemetry restart_request and relaunches the stopped lanes that asked, the scheduled headless reader. Use when: 'launch my lanes', 'restart the loop lanes', 'start the work lanes', 'morning lane refresh', 'stop a lane', 'which lanes are running', 'lane status', 'consume restart requests', 'lane restart consumer', 'relaunch the lanes that asked'. Mutating and operator-initiated; never touches a session whose name is not a configured lane."
claude-code-plugins
by melodic-software
"Slowness diagnostic that never 'fixes', run before restarting or deleting: version, retention sweep, install bloat, hook/subagent fan-out, kernel-leak census. Use when: 'Claude Code is slow', 'typing lags', 'my machine freezes when Claude runs', 'audit performance', 'why is this session sluggish', 'diagnose Claude slowness before I nuke anything', 'my hooks are slowing everything down', 'too many subagents'. Upstream bugs: /claude-ops:known-issues. Stale files: /claude-ops:audit-install-state."
claude-code-plugins
by melodic-software
"Verify the context-guard plugin's wiring on this machine: jq, node, the installed statusline shim, statusline wiring (including legacy version-pinned plugin-cache paths), and live-session snapshot freshness. Print the exact statusline edit for the operator, and install the shim plus seed ~/.claude/context-guard/zones.json from the shipped defaults. Use when: 'set up context-guard', 'is the context tee working', 'wire the context statusline', a consumer reports zone unknown in a live session, or after a plugin update. Actions: check (read-only; never edits settings), apply (writes ONLY inside ~/.claude/context-guard/, the shim and zones.json, on explicit request)."
claude-code-plugins
by melodic-software
"Configure the autonomy plugin for this repository: discover the adopting org's state (role homes, substrate availability, budget posture), interview where discovery cannot infer, and write the schema-versioned binding under .claude/autonomy/. Use when: 'set up autonomy', 'autonomy setup', 'configure autonomy', 'bind the autonomy contracts', or another autonomy capability reports a missing binding. Re-runnable. Safe to invoke again to reconfigure."
claude-code-plugins
by melodic-software
"When the bundled simplify skill resolves in this session, prefer it for the current diff; this skill for proactive lane hunts. Proactively hunt a rotated lane for Beck tidyings and ship one structure-only PR. Use when: 'tidy', 'tidy up', 'boy scout', 'polish', 'small refactors', 'improve gradually', 'clean up in passing', 'tidying day', 'tidy lane', 'run tidy'. Skip when /simplify refines the current diff; batch-simplify processes a diff window; issue-tracker work drains already-filed items."
claude-code-plugins
by melodic-software
"Audit a repo's Claude Code automation (hooks, MCP servers, skills, subagents, scheduled tasks) against the enforcement hierarchy, with evidence-backed PASS/REJECT/CONDITIONAL verdicts, REJECT by default. Use when: 'audit automations', 'what automations should we add', 'are we missing any hooks', 'hook gap analysis', 'should I add an MCP server for X'; pass --implement to apply approved items, or filter by category (hooks mcp skills subagents scheduled)."
Memory Health
by melodic-software
"Audit the Claude Code instruction/memory layer covering CLAUDE.md, a root AGENTS.md, CLAUDE.local.md, .claude/rules/, and auto-memory against a codified checklist derived from official Claude Code documentation. Use when: 'audit CLAUDE.md', 'audit AGENTS.md', 'memory health', 'audit rules', 'is my CLAUDE.md too long', 'prune instructions', after CLAUDE.md/rules changes or a Claude Code upgrade; actions: audit (default), fix, update, report."