documentation-discipline

documentation-discipline is a skill for Claude Code from volodchenkov/claude-sdlc-agents. It costs 76 tokens per session (3,102 once invoked), scanned A, original, MIT.

A set of rules for keeping code documentation up to date when implementation work is finished, including docstrings, README files, API notes, and migration notes.

In plain words
What is it for?
Use it after coding changes to decide what documentation to add or update and where it belongs.
Why use it?
It prevents completed code from being left without the explanations and project records needed to maintain it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sdlc-agents plugin — 12 skills, 13 agents shipped together

Good fit Use it after coding changes to decide what documentation to add or update and where it belongs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/volodchenkov/claude-sdlc-agents/documentation-discipline
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.

Any agent
npx skills add volodchenkov/claude-sdlc-agents --skill documentation-discipline
Clone the repo
git clone --depth 1 https://github.com/volodchenkov/claude-sdlc-agents

Made for: Claude Code.

Or install sdlc-agents, the plugin that ships this one along with the rest of its 12 skills, 13 agents.

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 documentation-discipline

README.md
[![agentmods](https://agentmods.dev/badge/skills/volodchenkov/claude-sdlc-agents/documentation-discipline/github.svg)](https://agentmods.dev/skills/volodchenkov/claude-sdlc-agents/documentation-discipline)
Your own site
<a href="https://agentmods.dev/skills/volodchenkov/claude-sdlc-agents/documentation-discipline"><img src="https://agentmods.dev/badge/skills/volodchenkov/claude-sdlc-agents/documentation-discipline/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 documentation-discipline

Your own site · 80×15
<a href="https://agentmods.dev/skills/volodchenkov/claude-sdlc-agents/documentation-discipline"><img src="https://agentmods.dev/badge/skills/volodchenkov/claude-sdlc-agents/documentation-discipline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,102 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 $0.00076 $0.03102
Opus 5 $0.00038 $0.01551
Sonnet 5 $0.00015 $0.00620
Haiku 4.5 $0.00008 $0.00310

Measured 8d ago against content hash f9f643b33912, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

documentation-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 8d 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.

skills/documentation-discipline/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Discipline

Rule: the author of the change owns the documentation. No one else picks it up after you. Code without documentation is incomplete — it stays in PLAN, not in CHANGES.


What to document, when, where

1. Docstrings (Python — )

A common Django setup uses Sphinx with napoleon extension (<backend-app>/docs/source/conf.py). Style: Google-style docstrings (napoleon's default and most readable).

When: every non-trivial function / class / module you add OR significantly modify.

Where: in the file, immediately after the def / class line.

Google-style format:

def calculate_delivery_estimate(order, region):
    """Estimate the delivery date for an order to a region.

    Combines carrier SLA (CDEK / Yandex), warehouse processing time,
    and the region's holiday calendar.

    Args:
        order: Order instance to estimate delivery for.
        region: Region instance (destination).

    Returns:
        datetime.date — the expected delivery date in region's local TZ,
        the latest of (now + carrier SLA) and (next working day in region).

    Raises:
        ValueError: if region has no carrier configured.
    """

Class docstrings:

class OrderViewSet(ModelViewSet):
    """REST endpoints for customer-facing order management.

    Filtered by `request.user.company` — multitenancy enforced.
    Customer can list / retrieve their own orders, cancel pending ones.
    Admin actions (status change, refund) are in employees.orders.
    """

Module docstring (top of models.py, services.py, etc.):

"""Customer-facing order domain.

Aggregates: Order, OrderItem, OrderHistory.
Owns the customer side of the order lifecycle (placement → cancellation).
Admin-side mutations are delegated to `employees.orders`.
"""

Skip: trivial getters / one-line setters / obvious property declarations. Comments noise = bad.

Module-level RST files: each Django app has a .rst in <backend-app>/docs/source/<app>.rst for architectural overview. When adding a new app or significantly changing one — update or create the corresponding RST.

Read the full file on GitHub · 301 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. 8d ago First seen · 301 lines · 76 tokens per session scan A f9f643b33912

Subscribe to this mod's changes

documentation-discipline is a skill published in the GitHub repository volodchenkov/claude-sdlc-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 3,102 once invoked, about $0.0004 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.