doctrine

doctrine is a command for Claude Code from Caxson/proof-of-work. It costs 21 tokens per session (292 once invoked), scanned A, original, Apache-2.0.

A command that reloads an engineering doctrine and treats its principles as binding for the rest of the session. The doctrine emphasizes reading evidence, finding root causes, preserving data, testing realistic paths, and checking work independently.

In plain words
What is it for?
It is for enforcing a proof-of-work approach during coding, debugging, integration, testing, and verification tasks.
Why use it?
It reminds the agent to investigate failures carefully and avoid guesses, shortcuts, or fixes that only hide symptoms.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the proof-of-work plugin — 2 skills, 3 commands, 1 hook shipped together

Good fit It is for enforcing a proof-of-work approach during coding, debugging, integration, testing, and verification tasks.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/caxson/proof-of-work/doctrine
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.

Clone the repo
git clone --depth 1 https://github.com/Caxson/proof-of-work

Made for: Claude Code.

Or install proof-of-work, the plugin that ships this one along with the rest of its 2 skills, 3 commands, 1 hook.

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 doctrine

README.md
[![agentmods](https://agentmods.dev/badge/commands/caxson/proof-of-work/doctrine/github.svg)](https://agentmods.dev/commands/caxson/proof-of-work/doctrine)
Your own site
<a href="https://agentmods.dev/commands/caxson/proof-of-work/doctrine"><img src="https://agentmods.dev/badge/commands/caxson/proof-of-work/doctrine/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for doctrine

Your own site · 80×15
<a href="https://agentmods.dev/commands/caxson/proof-of-work/doctrine"><img src="https://agentmods.dev/badge/commands/caxson/proof-of-work/doctrine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 292 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00021 $0.00292
Opus 5 $0.00010 $0.00146
Sonnet 5 $0.00004 $0.00058
Haiku 4.5 $0.00002 $0.00029

Measured 9d ago against content hash cca51fe8b35e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

doctrine 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 9d 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.

commands/doctrine.md · 26 lines

What it actually says

Reload and obey the proof-of-work Engineering Doctrine for the rest of this session. Restate it in your own words, then follow it. The principles:

  1. Attribution discipline — assume the bug is yours first; read logs before asserting any cause; a different cause each time means you're guessing.
  2. Engineer around blockers — route around them, don't blame the environment; don't switch the agreed stack without asking.
  3. Root cause, not symptom — never delete data or run on degraded/incomplete state to "work around" a problem.
  4. Abstraction over special-casing — solve the class of problem; regex/if-else only for genuine special cases.
  5. Integrate across modules — exercise cross-module contracts; if unsure how they connect, ASK.
  6. Test horizontally, like a real user — many realistic paths, not one happy path.
  7. Don't wait to be scolded — treat correction as evidence you're wrong; re-examine instead of re-defending.
  8. Stop only for the right reason — "stop after N failures" is valid only after ruling out your own cause with evidence.
  9. Use subagents & workflows to verify — independent/adversarial perspective; orchestrate multi-step verification.
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. 9d ago First seen · 26 lines · 21 tokens per session scan A cca51fe8b35e

Subscribe to this mod's changes

doctrine is a command published in the GitHub repository Caxson/proof-of-work (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 292 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.