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 commands/everyone-needs-a-copilot/claude-copilot/knowledge-copilotgit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote 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/commands/everyone-needs-a-copilot/claude-copilot/knowledge-copilot)<a href="https://agentmods.dev/commands/everyone-needs-a-copilot/claude-copilot/knowledge-copilot"><img src="https://agentmods.dev/badge/commands/everyone-needs-a-copilot/claude-copilot/knowledge-copilot.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 5.1 | $0.00000 | $0.00713 |
| Opus 5 | $0.00000 | $0.00357 |
| Sonnet 5 | $0.00000 | $0.00143 |
| Haiku 4.5 | $0.00000 | $0.00071 |
Grade A, and why
knowledge-copilot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Copilot — Bootstrapper
Locates the Knowledge Copilot repository on this machine, then hands off to the methodology inside it. This command is a thin bootstrapper; the substantive KMS-building methodology lives in the repo at docs/00-knowledge-copilot/01-build-a-kms.md.
Step 1 — Hydrate env vars
eval "$(cc env)"
This populates CC_KNOWLEDGE_REPO (and CC_SHARED_DOCS) if the machine config has a path set.
Step 2 — Locate the Knowledge Copilot repo
Resolve REPO_PATH by checking these sources in order; stop at the first hit:
# 1. Canonical env var (set via cc env)
echo "${CC_KNOWLEDGE_REPO:-}"
# 2. Config lookup (in case env wasn't hydrated this session)
cc config get paths.knowledge_repo 2>/dev/null && echo "FOUND_CONFIGURED"
# 3. Generic install location (symlink at ~/.claude/knowledge)
readlink -f ~/.claude/knowledge 2>/dev/null
Set REPO_PATH to the first resolved path. If none resolve, proceed to Step 3.
Step 3 — If repo not found: guide the user
The canonical GitHub repo during transition:
- Current name:
https://github.com/Everyone-Needs-A-Copilot/knowledge-copilot - Future canonical:
https://github.com/Everyone-Needs-A-Copilot/knowledge-copilot
Ask the user (use AskUserQuestion):
Question: "No Knowledge Copilot repo found on this machine. What would you like to do?" Header: "Setup" Options:
- "Clone the canonical repo" — ask where to put it (default: a sibling directory next to this project), then
git clone [email protected]:Everyone-Needs-A-Copilot/knowledge-copilot.git "$REPO_PATH" - "Create a new knowledge repo" — start fresh with guided discovery
- "Link an existing local repo" — provide a path
After cloning or creating, set REPO_PATH and register it:
cc config set paths.knowledge_repo "$REPO_PATH"
cc config set paths.shared_docs "$REPO_PATH"
Then continue to Step 4.
Step 4 — Hand off to in-repo methodology
With REPO_PATH resolved, read the methodology document:
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.
- yesterday First seen · 83 lines · 0 tokens per session scan A 4fbc12cb6ee2
knowledge-copilot is a command published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 713 tokens. 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 2026-09-04.
Other commands, from other repositories
gohm
Persona: You are the Knowledge Harvester -- you extract signal from noise, turning session work into durable organizational memory. Reflection Protocol: See agents/reflection-protocol.md for reflection requirements.
memory
You are the Memory Curator, the guardian of NASAB Pillar 5: Permanent Memory. You ensure that nothing is ever deleted from the knowledge base - only the retrieval path changes. You are the librarian of an infinite library where every book remains on the shelf, but some are easier to find than others.
context
You are the Context Manager, responsible for monitoring and optimizing context usage during long implementation sessions. You help prevent context overflow and maintain efficiency.
recall
/recall "query" Search and show compact index /recall "query" --type=decision Filter by entry type /recall "query" --min-weight=0.7 Filter by minimum weight /recall "query" --since=7d Filter by recency /recall "query" --tags=auth,security Filter by tags /recall --preview id1,id2,id3 Show content summaries for specific…
INFO
Каждый новый терминал = новая сессия = пустой контекст. Агент не знает по какому проекту работаем, какой стек, какие серверы, где деплой, какие активные задачи. Пользователь вынужден на каждом старте перечислять одно и то же — теряется время и мысль.
vulyk-gc
Memory garbage collection - consolidate learnings, prune stale pointers, clean snapshots.