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.
npx skills add viktorbezdek/skillstack --skill documentation-disciplinegit clone --depth 1 https://github.com/viktorbezdek/skillstackWrote 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.
[](https://agentmods.dev/skills/viktorbezdek/skillstack/documentation-discipline)<a href="https://agentmods.dev/skills/viktorbezdek/skillstack/documentation-discipline"><img src="https://agentmods.dev/badge/skills/viktorbezdek/skillstack/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.
<a href="https://agentmods.dev/skills/viktorbezdek/skillstack/documentation-discipline"><img src="https://agentmods.dev/badge/skills/viktorbezdek/skillstack/documentation-discipline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00132 | $0.02184 |
| Opus 5.5 | $0.00053 | $0.00874 |
| Sonnet 5.5 | $0.00026 | $0.00437 |
| Haiku 4.5 | $0.00013 | $0.00218 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Discipline
Under-documentation forces re-discovery. Over-documentation forces maintenance. The discipline is to write what will be re-used, at the altitude it will be re-used, and to let the rest stay in chat.
What to write down (the decision tree)
Is the question likely to be asked again?
├── No → don't document (Slack thread is fine)
└── Yes → keep going ↓
Is the answer likely to change often?
├── Yes → runbook or FAQ (owned + dated)
└── No → keep going ↓
Is the answer a decision with long-term consequences?
├── Yes → ADR (immutable, numbered, dated)
└── No → keep going ↓
Is the answer operational (how to do X)?
├── Yes → runbook
└── No → one-pager or reference doc
Red flags that you are under-documenting:
- The same question comes up every quarter.
- New hires ask the same question every cohort.
- "Tribal knowledge" is a phrase anyone uses non-ironically.
- A critical operation has to be learned by watching someone else do it.
Red flags that you are over-documenting:
- Docs are out of date within a month of writing.
- More than 20% of docs have no owner.
- Searches return 5 contradictory answers.
- Writing the doc took longer than doing the thing.
Architecture Decision Records (ADRs)
An ADR captures an architecture decision and the reasoning behind it. Once published, an ADR is immutable — if the decision changes, you write a new ADR that supersedes the old one.
ADR template
# ADR-NNNN: [Title — a noun phrase]
**Date:** YYYY-MM-DD
**Status:** Proposed / Accepted / Superseded by ADR-MMMM / Deprecated
**Deciders:** [names]
## Context
What forced the decision? What constraints exist? What was true when this was decided?
(Keep short — 1-3 paragraphs. Do not re-litigate history.)
## Decision
What did we decide, stated as a present-tense claim. One paragraph.
## Consequences
- **Positive:** what we gain
- **Negative:** what we give up
- **Neutral:** what we accept (trade-offs not clearly positive or negative)
## Alternatives considered
- [Option] — why not chosen (one sentence each)
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 244 lines · 132 tokens per session scan A b0720f4f60e2
documentation-discipline is a skill published in the GitHub repository viktorbezdek/skillstack (14 stars, last pushed 4mo ago), licensed MIT. It adds 132 tokens to every session and 2,184 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
agents-v2-py
Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.
analytics-product
Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.
api-security-best-practices
Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities.
analytics-tracking
Design, audit, and improve analytics tracking systems that produce reliable, decision-ready data.
antigravity-workflows
Use when asked to ship a SaaS MVP, audit application security, build an AI agent, run browser QA, or design a domain model with multiple skills and verified checkpoints.
agent-tool-builder
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.