Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/qball-inc/clear/cf-debugnpx skills add QBall-Inc/clear --skill cf-debuggit clone --depth 1 https://github.com/QBall-Inc/clearWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00029 | $0.01514 |
| Opus 5 | $0.00015 | $0.00757 |
| Sonnet 5 | $0.00006 | $0.00303 |
| Haiku 4.5 | $0.00003 | $0.00151 |
Grade A, and why
cf-debug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Usage: When unsure about a CLI's interface or flags, run it with
--helpfirst. Do NOT attempt to discover functionality by reading plugin source code — doing so leads to incorrect execution from assumptions made without context of the holistic flow.
CLEAR Debug & Diagnostics
Validate CLEAR framework state across all domains (sync, workpackage, plan, knowledge, session) and optionally auto-repair fixable issues. Routes to the debug CLI tool for execution.
Plugin Root Resolution
CLI commands in this skill reference $CLEAR_PLUGIN_ROOT — a .claude/settings.json env var the shell expands. The SessionStart hook persists it, but settings env vars load at session launch, so on a brand-new consumer's first session (before its next restart) the variable is empty and node "$CLEAR_PLUGIN_ROOT/build/..." fails with MODULE_NOT_FOUND.
First-session bootstrap — if $CLEAR_PLUGIN_ROOT is empty, set it inline in the same Bash call as the CLI (each Bash call is a fresh shell, so a separate export would not carry over):
export CLEAR_PLUGIN_ROOT="${CLEAR_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}"
Prepend it to the CLI in one shell line: export CLEAR_PLUGIN_ROOT="${CLEAR_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}"; <node "$CLEAR_PLUGIN_ROOT/build/..." command>. ${CLAUDE_PLUGIN_ROOT} resolves in this SKILL.md body to the actually-loaded plugin path; once the consumer restarts, $CLEAR_PLUGIN_ROOT is populated and the assignment is a harmless no-op.
When to Use This Skill
Load this skill when the user request matches ANY of these patterns:
| Trigger Pattern | Example User Request |
|---|---|
| Diagnose or debug CLEAR state | "Run CLEAR diagnostics" |
| Check for state inconsistencies | "Something seems wrong with my CLEAR state" |
| Repair CLEAR issues | "Fix my CLEAR configuration issues" |
| Validate domain integrity | "Check if my workpackages are valid" |
| Health check before session | "Verify CLEAR is healthy before we start" |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 168 lines · 0 tokens per session scan A ee3ade5826ae
cf-debug is a skill published in the GitHub repository QBall-Inc/clear (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,514 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
implement
End-to-end workflow for taking MCP work items from backlog to merged PR. Handles git branching, schema-driven planning, implementation, independent review, and PR creation. Composes spec-quality, review-quality, and schema-workflow skills into a single pipeline. Use when a user says "implement this", "work on this…
session-retrospective
Analyzes the current implementation run — evaluates schema effectiveness, delegation alignment, note quality, and plan-to-execution fit. Captures cross-session trends and proposes improvements when patterns repeat. Use after implementation runs, or when user says 'retrospective', 'session review', 'what did we learn'…
ralph
Launcher for the Ralph-style queue drain script — emits the right node ralph-loop.mjs invocation based on the user's filter and bounds. The actual loop runs as a Node script that spawns one claude -p --worktree per iteration; this skill is the configurator, not the loop. Use when a user says: drain the backlog, ralph…
prepare-release
End-to-end release automation — reads commits since last tag, infers semver bump, drafts changelog, creates release PR, merges it, waits for CI green, tags, and monitors the Docker build to completion. Use when the user says: prepare release, cut a release, bump version, create release PR, ship a new version, tag a…
quick-start
Interactive onboarding for the MCP Task Orchestrator. Detects empty or populated workspaces and walks through how plan mode, persistent tracking, and the MCP work together. Use when a user says "get started", "how do I use this", "quick start", "first time setup", "onboard me", "what can this MCP do", or "help me…
review-proposals
Triages pending improvement-proposal MCP items — presents each with its scope and evidence, collects an accept/reject/defer decision per proposal, and carries out the disposition: project-scoped acceptances get their exact YAML applied to .taskorchestrator/config.yaml and pushed per-root; global acceptances get a…