ck-charter

A command for viewing and managing the active task charter, which is a saved list of code constraints with file-and-line citations. The charter can be refreshed when lines move or cleared when the task changes.

In plain words
What is it for?
Use it to inspect the current charter, refresh citations after code changes, or remove it before starting a different task.
Why use it?
It keeps important implementation constraints visible during later edits and avoids silently trusting outdated citations.

Command

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 commands/pinperepette/context-kernel/ck-charter
Clone the repo
git clone --depth 1 https://github.com/Pinperepette/context-kernel
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 351 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 $0.00033 $0.00351
Opus 5 $0.00016 $0.00176
Sonnet 5 $0.00007 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 2d ago against content hash 93fd35203e6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ck-charter 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.

claude-context-kernel/commands/ck-charter.md · 27 lines

What it actually says

context-kernel — charter (carta del task)

Argomenti: $ARGUMENTS

La carta è l'insieme dei vincoli che il fix deve rispettare, ognuno con citazione file:riga. Quando è salvata diventa attiva: una guardia PreToolUse inietta i vincoli rilevanti prima di ogni Edit/Write/Bash sui file citati, e sopravvive all'auto-compact.

  • get (default) → mostra la carta attiva:
    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/charter.py" get
    
  • refresh → ri-risolve deterministicamente i file:riga driftati contro l'anchor catturato al save. Match unico → aggiorna; zero o ambiguo → dichiarato irrisolvibile, mai indovinato:
    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/charter.py" refresh
    
  • clear → azzera la carta (usalo quando il task è cambiato):
    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/charter.py" clear
    

Se non c'è carta attiva, dillo in una riga e suggerisci che la carta si genera dalla pipeline kernel (skill kernel-invariants / kernel-pipeline).

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. 2d ago First seen · 27 lines · 33 tokens per session scan A 93fd35203e6a

Subscribe to this mod's changes

ck-charter is a command published in the GitHub repository Pinperepette/context-kernel (24 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 351 once invoked, about $0.0002 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 2026-08-30.