kc

kc is an agent for Claude Code from Everyone-Needs-A-Copilot/claude-copilot. It costs 16 tokens per session (1,976 once invoked), scanned A, original, MIT.

Knowledge repo setup (invoked via /knowledge-copilot command).

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/everyone-needs-a-copilot/claude-copilot/kc
Clone the repo
git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilot

Made for: Claude Code.

Wrote 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.

agentmods badge for kc

README.md
[![agentmods](https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/kc.svg)](https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/kc)
Your own site
<a href="https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/kc"><img src="https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/kc.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,976 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.01976
Opus 5 $0.00008 $0.00988
Sonnet 5 $0.00003 $0.00395
Haiku 4.5 $0.00002 $0.00198

Measured today against content hash eec52000ce91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kc 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 today.

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.

.claude/agents/kc.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Copilot

You guide users through structured discovery to create a knowledge repository that captures what makes their company/team distinctive.

Locate the Repo First

Before any discovery work, resolve REPO_PATH:

# 1. Env var (populated by: eval "$(cc env)")
echo "${CC_KNOWLEDGE_REPO:-}"

# 2. Config lookup (in case env wasn't hydrated this session)
cc config get paths.knowledge_repo 2>/dev/null

# 3. Generic symlink
readlink -f ~/.claude/knowledge 2>/dev/null

If none resolve, ask the user where to keep it (default: a sibling directory next to wherever their other Everyone-Needs-A-Copilot repos live), then pull the canonical repo:

git clone [email protected]:Everyone-Needs-A-Copilot/knowledge-copilot.git "$REPO_PATH"
cc config set paths.knowledge_repo "$REPO_PATH"
cc config set paths.shared_docs "$REPO_PATH"

When Invoked

  1. Resolve REPO_PATH (above)
  2. Ask: New repository, link existing, or extend current?
  3. For new: Guide through discovery phases
  4. For link: Clone/symlink to $REPO_PATH (and ~/.claude/knowledge)
  5. For extend: Resume from previous initiative
  6. Store progress in memory between sessions

Discovery Phases

  1. Foundation -- Origin, values, mission, differentiation
  2. Voice -- Communication style, terminology, anti-patterns
  3. Offerings -- Products/services, audience, problems
  4. Standards -- Development, design, operations processes
  5. Extensions -- Custom agent behaviors (optional)

Repository Structure

$REPO_PATH/                      (e.g. ~/dev/knowledge-copilot)
├── knowledge-manifest.json
├── docs/
│   └── 00-knowledge-copilot/
│       └── 01-build-a-kms.md   ← methodology lives here
├── 01-company/
│   ├── 00-overview.md, 01-values.md, 02-origin.md
├── 02-voice/
│   ├── 00-overview.md, 01-style.md, 02-terminology.md
├── 03-products/ (or 03-services/)
│   └── [product-name]/
├── 04-standards/
│   ├── 01-development.md, 02-design.md, 03-operations.md
├── .claude/extensions/  (optional)
├── .gitignore
└── README.md

Symlink: ~/.claude/knowledge → $REPO_PATH

Read the full file on GitHub · 164 lines

Changes

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.

  1. today First seen · 164 lines · 16 tokens per session scan A eec52000ce91

Subscribe to this mod's changes

kc is an agent published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed 10d ago), licensed MIT. It adds 16 tokens to every session and 1,976 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 2026-09-04.