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/knowledge-managementnpx skills add QBall-Inc/clear --skill knowledge-managementgit clone --depth 1 https://github.com/QBall-Inc/clearWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/qball-inc/clear/knowledge-management)<a href="https://agentmods.dev/skills/qball-inc/clear/knowledge-management"><img src="https://agentmods.dev/badge/skills/qball-inc/clear/knowledge-management.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00024 | $0.05329 |
| Opus 5 | $0.00012 | $0.02665 |
| Sonnet 5 | $0.00005 | $0.01066 |
| Haiku 4.5 | $0.00002 | $0.00533 |
Grade A, and why
knowledge-management 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 4d 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 — 364 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.
Knowledge Management Skill
Purpose
This skill provides guidance for Claude on managing persistent project knowledge in the CLEAR framework. It covers capturing decisions, searching the knowledge base, viewing entries, managing lifecycle (linking, deprecation, supersession, update, deletion), and understanding automatic knowledge hooks.
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. Reference files are left unchanged.
Command Reference
All CLIs at $CLEAR_PLUGIN_ROOT/build/infrastructure/knowledge/cli/. Run with --clear-dir=./.clear.
| Action | CLI Command |
|---|---|
| Create new entry | capture-cli --create --type=<type> --title="..." --description="..." |
| Update entry fields (tags, description) | capture-cli --update --id=<id> --tags="..." --description="..." |
| Change entry type (regenerates ID) | capture-cli --update --id=<id> --type=<new-type> |
| Add file link to entry | capture-cli --update --id=<id> --add-related-file=<path> |
| Search knowledge base | search-cli --query="..." |
| Show entry details | show-cli --id=<id> |
| Knowledge base overview | status-cli |
| Link entry to workpackage | link-cli link <id> --to=<wp-id> |
| Unlink from workpackage | link-cli unlink <id> |
| Deprecate entry | deprecate-cli <id> --reason="..." |
| Supersede entry | supersede-cli <old-id> <new-id> |
| Delete entry | delete-cli <id> --reason="..." --force |
| Rebuild search index | index-cli --mode=full --force |
| Incremental index update | index-cli --mode=incremental |
| File-to-entry lookup | file-index-cli --lookup=<path> |
| Rebuild file index | file-index-cli --rebuild |
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.
- 4d ago First seen · 364 lines · 24 tokens per session scan A 86d52e294257
knowledge-management is a skill published in the GitHub repository QBall-Inc/clear (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 5,329 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
session-trends
Analyze trends across session metrics. Computes windowed aggregates, deltas, and compares against MEMORY.md findings. Use periodically for progress tracking.
assigns-audit
Inspect LiveView socket assigns for memory bloat — missing temporaryassigns, unused assigns, unbounded lists needing streams, memory estimates. Use when LiveView memory grows or you need to add temporaryassigns.
engram
Read and write the project's durable reasoning memory (decisions, principles, cautions, problems, insights) through the Engram MCP tools. Recall relevant memory before non-trivial work; capture only durable, high-value knowledge silently at natural stopping points; keep the graph honest (judge suspects, close answered…
engram-digest
Seed or top up this project's Engram graph from the existing codebase — an explicit, user-invoked digestion of the current working tree into typed memory nodes (decisions, principles, cautions, problems, insights, intents). Use when the user says "digest this project", "ingest the codebase into memory", "seed the…
garden-tending
Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…
curator-practice
Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs…