A session-start plugin for reducing repeated context and token use in Claude Opus 5 coding sessions. It provides a fixed 220-token instruction block and evidence supporting its rules, including a benchmark of 106 tasks.

Use it to configure token-conscious coding sessions, inspect the evidence behind the defaults, and apply the supplied instruction block.

It targets waste from resending and rereading context, while documenting the trade-offs of compressing agent responses and behavior.

discipline — Plugin by fledgeling-co

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.

Claude Code

/plugin marketplace add fledgeling-co/fledgeling-plugins

agentmods

npx agentmods add plugins/fledgeling-co/fledgeling-plugins/discipline

Clone the repo

git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

discipline 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.

plugins/discipline/.claude-plugin/plugin.json · 18 lines

What it actually says

{
  "name": "discipline",
  "description": "Session-start operating defaults that cut token spend without cutting task success, tuned for Claude Opus 5 agentic coding. Ships a byte-stable 220-token block for the cached system prefix plus the measured evidence behind every clause, including a paired 106-task benchmark showing that caveman-style response compression cost 7.6 points of task score on Opus 5, with 78% of its apparent saving coming from the agent taking fewer steps rather than writing more tersely.",
  "version": "4.3.0",
  "author": {
    "name": "Fledgeling",
    "email": "[email protected]"
  },
  "license": "MIT",
  "keywords": [
    "tokens",
    "cost",
    "prompt-cache",
    "opus-5",
    "agentic-coding"
  ]
}

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.

2d ago First seen · 18 lines scan A 60cdbb4a0997

Subscribe to this mod's changes

discipline is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Planning

discipline

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

humanizer

nextjs

nextjs

claude-plugins-official

knowledge-work-plugins

ecc