charter-evolve

charter-evolve is a command for coding agents from elbalen/skopus. It costs 16 tokens per session (956 once invoked), scanned A, original, MIT.

A session-end command for reviewing the conversation and recording corrections, confirmed decisions, and new working rules in feedback files. It is part of an agent partnership charter.

In plain words
What is it for?
Use it after substantive sessions to capture what changed, what worked, and what the agent should remember.
Why use it?
It preserves lessons from the session so future work can follow the user’s preferences and avoid repeated mistakes.

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/elbalen/skopus/charter-evolve
Clone the repo
git clone --depth 1 https://github.com/elbalen/skopus

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 charter-evolve

README.md
[![agentmods](https://agentmods.dev/badge/commands/elbalen/skopus/charter-evolve.svg)](https://agentmods.dev/commands/elbalen/skopus/charter-evolve)
Your own site
<a href="https://agentmods.dev/commands/elbalen/skopus/charter-evolve"><img src="https://agentmods.dev/badge/commands/elbalen/skopus/charter-evolve.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 956 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 $0.00956
Opus 5 $0.00008 $0.00478
Sonnet 5 $0.00003 $0.00191
Haiku 4.5 $0.00002 $0.00096

Measured 4d ago against content hash 092b203f41ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

charter-evolve 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.

skopus/templates/commands/charter-evolve.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/charter-evolve

The compounding mechanism for the partnership charter. Run this at the end of every substantive session. It captures what happened so the next session starts smarter.

This runs inside the agent, not the shell. The agent reviews the full conversation history and extracts knowledge — no manual input needed.

Steps

  1. Review the full conversation history. Look for:

    • Corrections — moments where the user said "no", "don't do that", "use X instead", or pushed back on an approach. Each correction is a drift.
    • Validated calls — moments where the agent made a non-obvious choice and the user confirmed it worked ("yes exactly", "perfect", "keep doing that", accepted without pushback). These are easy to miss — watch for them.
    • New rules — any explicit instruction the user gave about how to work going forward ("always X", "never Y", "from now on Z").
  2. For each item found, write a feedback file at ~/.skopus/memory/feedback/YYYY-MM-DD-<slug>.md using this format:

    ---
    name: <kind>-<slug>
    description: <one-line description>
    type: feedback
    captured: YYYY-MM-DD
    ---
    
    # <Title>
    
    **Why:** <why this matters — the reason the user gave or the context>
    
    **How to apply:** <when and where this rule kicks in — be specific>
    
  3. Append drift entries to the charter. Open ~/.skopus/charter/workflow_partnership.md and append each correction to Section 7 (Where We've Drifted) in this format:

    > **YYYY-MM-DD — <what I did wrong>.** <context>. **Correction:** <what the user said>. **Fix:** <the rule to follow next time>.
    
  4. Append validated calls to the charter. In the same file, append each win to Section 8 (What Has Worked):

    - **YYYY-MM-DD — <what I did right>.** <why it worked>. *(How: <how to repeat it>)*
    
  5. Update the memory index. Add a one-line entry for each new feedback file to ~/.skopus/memory/MEMORY.md under the Feedback Memory section:

Read the full file on GitHub · 89 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. 4d ago First seen · 89 lines · 16 tokens per session scan A 092b203f41ef

Subscribe to this mod's changes

charter-evolve is a command published in the GitHub repository elbalen/skopus (4 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 956 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.