agent-glovebox: Skill for Claude Code

.claude/skills/doctrine-capture/SKILL.md

doctrine-capture is a skill for Claude Code from AlexanderMattTurner/agent-glovebox. It costs 96 tokens per session (1,212 once invoked), scanned C, original, Apache-2.0.

A workflow for recording permanent project rules when a user says something should always or never happen. It writes the rule into the repository so later sessions can follow it.

In plain words
What is it for?
It helps capture standing rules, update repository guidance, and distinguish lasting instructions from one-time requests.
Why use it?
It prevents important instructions from disappearing when a conversation ends and helps correct the current mistake before recording the rule.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is AlexanderMattTurner/agent-glovebox's own configuration. It tells Claude Code how to work on agent-glovebox itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-glovebox configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AlexanderMattTurner/agent-glovebox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AlexanderMattTurner/agent-glovebox/main/.claude/skills/doctrine-capture/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AlexanderMattTurner/agent-glovebox

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 doctrine-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexandermattturner/agent-glovebox/doctrine-capture/github.svg)](https://agentmods.dev/skills/alexandermattturner/agent-glovebox/doctrine-capture)
Your own site
<a href="https://agentmods.dev/skills/alexandermattturner/agent-glovebox/doctrine-capture"><img src="https://agentmods.dev/badge/skills/alexandermattturner/agent-glovebox/doctrine-capture/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-capture

Your own site · 80×15
<a href="https://agentmods.dev/skills/alexandermattturner/agent-glovebox/doctrine-capture"><img src="https://agentmods.dev/badge/skills/alexandermattturner/agent-glovebox/doctrine-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,212 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00096 $0.01212
Opus 5 $0.00048 $0.00606
Sonnet 5 $0.00019 $0.00242
Haiku 4.5 $0.00010 $0.00121

Measured 2d ago against content hash e190659189d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

doctrine-capture scanned grade C with 1 finding 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.

Instruction-override phrasinghighPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

3. **Root `CLAUDE.md`** takes it only when it must fire BEFORE any file is opened, or must override the system prompt. That is a small set, and everything else that lands there taxes every unrelated session.
.claude/skills/doctrine-capture/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capturing a NEVER or an ALWAYS

The doctrine

A capitalised NEVER or ALWAYS from the user is a standing rule, and you are the only one who will ever hear it. The conversation ends and the next session starts from the committed tree, so a rule you merely obey this turn is a rule you deleted. Obey it now AND write it down, in the same turn.

The user's own words are the human approval a doctrine change needs, when they state a STANDING rule. Root CLAUDE.md § Guard budget makes an edit to CLAUDE.md, .claude/rules/, .claude/skills/ or a committed agent prompt human-gated, and § Autonomy keeps such an edit a proposal except when a human approved it. A standing rule the user just stated IS that approval, so write it without asking, and quote their sentence in the PR body so a reviewer sees what authorised it. Anything short of a standing rule is not approved: apply the § What is NOT doctrine test below first, and leave it a proposal when the test does not pass.

Fix the instance first, then the rule. The user says NEVER about something you just did, so the artifact holding the mistake is still open. Correct it, then capture. A capture with the broken artifact still standing answers the complaint with a promise.

Which surface takes it

Root CLAUDE.md § Where the rest of the guidance lives already gives the narrowest-surface rule. Apply it to the three surfaces this workflow chooses between:

  1. A path gets a .claude/rules/ file whose paths: glob matches it. A rule about shell goes in shell-style.md, not in a skill nobody invoked.
  2. An activity gets the skill that owns it. A rule about how a PR body reads goes in pr-creation; a rule about copyable markdown goes in markdown-block.
  3. Root CLAUDE.md takes it only when it must fire BEFORE any file is opened, or must override the system prompt. That is a small set, and everything else that lands there taxes every unrelated session.

What is NOT doctrine

A rule binds future sessions; an instruction binds this one. The test: would this be right for a session that never saw this conversation?

Read the full file on GitHub · 54 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. 2d ago Changed · +9 lines scan D → C e190659189d8
  2. 5d ago Changed scan C → D 944586afd901
  3. 6d ago Changed cff274df7041
  4. 7d ago First seen · 45 lines · 96 tokens per session scan C ce91fe8cc42e

Subscribe to this mod's changes

doctrine-capture is a skill published in the GitHub repository AlexanderMattTurner/agent-glovebox (62 stars, last pushed yesterday), licensed Apache-2.0. It adds 96 tokens to every session and 1,212 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens