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 attilaszasz/sdd-pilot --skill adr-authoringgit clone --depth 1 https://github.com/attilaszasz/sdd-pilotWrote 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/attilaszasz/sdd-pilot/adr-authoring)<a href="https://agentmods.dev/skills/attilaszasz/sdd-pilot/adr-authoring"><img src="https://agentmods.dev/badge/skills/attilaszasz/sdd-pilot/adr-authoring/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/attilaszasz/sdd-pilot/adr-authoring"><img src="https://agentmods.dev/badge/skills/attilaszasz/sdd-pilot/adr-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.01591 |
| Opus 5 | $0.00015 | $0.00796 |
| Sonnet 5 | $0.00006 | $0.00318 |
| Haiku 4.5 | $0.00003 | $0.00159 |
Grade A, and why
adr-authoring 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.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MADR Authoring Skill
Canonical rules for project-level Architecture Decision Records. All ADR file mutations flow through the ADR Author subagent (.github/agents/_adr-author.md). Orchestrating workflows (system-design, plan-feature, amend-project) decide when an ADR is needed; this skill defines what the ADR must look like and how it is managed.
Scope
- Project-level architectural decisions only.
- Standalone Markdown files under
specs/adrs/. - Feature-local tradeoffs stay in
plan.mdasAD-###rows and never invoke this skill.
MADR Profile
Required Frontmatter
---
adr_id: ADR-NNNN
status: proposed | accepted | deprecated | superseded
date: YYYY-MM-DD
tags: []
supersedes: []
superseded_by: ""
related_artifacts: []
---
Optional Frontmatter
deciders: []
consulted: []
informed: []
review_date: YYYY-MM-DD
Required Body Sections
# ADR-NNNN: Decision Title
## Status
[Mirrors frontmatter status in human-readable form. Include supersession links when applicable.]
## Context
[Problem, forces, constraints, and why a decision is needed now.]
## Decision Drivers
- [Criteria that drove the choice, ordered by weight]
## Considered Options
### Option A: [Label]
- Pros: …
- Cons: …
### Option B: [Label]
- Pros: …
- Cons: …
## Decision Outcome
Chosen option: **[Label]** — [rationale for selecting it].
## Consequences
### Positive
- …
### Negative
- …
### Neutral
- … *(optional)*
## Links
- [Related ADRs, PRD capabilities, feature specs, project-plan epics, external standards]
Numbering and File Naming
- Canonical identifier:
ADR-NNNN— four-digit, zero-padded, repository-global. - File naming:
specs/adrs/NNNN-decision-title.mdwheredecision-titleis lowercase ASCII kebab-case derived from the title. - Number allocation: scan
specs/adrs/for existing numbered files, resolve the highest allocatedNNNN, assign the next integer. Numbers are monotonic and never reused. - Path stability: once created, a file path must not be renamed solely because the title wording changes. Title corrections stay in the body/frontmatter; the original slug persists.
- Compatibility: readers should accept legacy three-digit references (
ADR-001) but all new output must use four-digit form (ADR-0001).
What ships with it
1 file 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.
- 9d ago First seen · 173 lines · 30 tokens per session scan A 3bf237528d91
adr-authoring is a skill published in the GitHub repository attilaszasz/sdd-pilot (96 stars, last pushed 7d ago), licensed MIT. It adds 30 tokens to every session and 1,591 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
universal-live-check
Universal live-check framework for coding agents. Executes incremental, deterministic validation across all software domains (CLI, backend, frontend, mobile, embedded, libs). Change-type-aware (feat, fix, hotfix, refactor, migrate, docs). Triggers whenever an agent needs to validate code quality, run linting, perform…
code-review-hardening
Use this skill for rigorous, structured code review with a self-repair loop. Applies change-type-aware strategies (feat, fix, hotfix, refactor, migrate, docs). Findings are severity-classified, then auto-fixed where possible. Triggers on PR reviews, code review requests, or when reviewing any change set.
contextual-stewardship
Use this skill when the user makes a technical decision, establishes a new pattern, defines business rules, or explicitly asks to remember or save a guideline. Also use this skill when you are about to implement a feature, write code, plan an architecture, or make a technical decision - you MUST retrieve contextual…
project-guidelines-writer
Use this skill when the user wants repository guidance documents generated or refreshed, including AGENTS.md, CONTRIBUTING.md, STYLEGUIDE.md, TESTING.md, ARCHITECTURE.md, and SECURITY.md. It analyzes the repository, generates all six guideline files by default, prefers managed-section updates for existing files, and…
quality-grading
Use this skill to grade code, specifications, or design documents across four quality dimensions using a 1-5 scoring scale. In grade-and-fix mode, the skill auto-improves artifacts scoring below 5 without prompting. Invoke when you want consistent quality assessment on design, implementation, or specification with…
spec-driven-task-decomposer
Use this skill when approved requirements and design need to be decomposed into tasks.md for Phase 3 of a Spec-Driven change. It creates atomic, traceable implementation and testing tasks, validates the plan, and should not be used to design architecture or write implementation code.