Borrowing it
Nothing to install: this file belongs to rigortype/rigor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rigortype/rigor/master/.claude/skills/rigor-adr-author/SKILL.mdgit clone --depth 1 https://github.com/rigortype/rigorWrote 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/rigortype/rigor/rigor-adr-author)<a href="https://agentmods.dev/skills/rigortype/rigor/rigor-adr-author"><img src="https://agentmods.dev/badge/skills/rigortype/rigor/rigor-adr-author/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/rigortype/rigor/rigor-adr-author"><img src="https://agentmods.dev/badge/skills/rigortype/rigor/rigor-adr-author.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 | $0.00056 | $0.02830 |
| Opus 5.5 | $0.00022 | $0.01132 |
| Sonnet 5.5 | $0.00011 | $0.00566 |
| Haiku 4.5 | $0.00006 | $0.00283 |
Grade A, and why
rigor-adr-author 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 11d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Author an ADR
This skill is the procedure for adding an ADR. The quality bar is
docs/adr/49-adr-authoring-guidelines.md
— read it; do not re-derive or restate its rubric here. The skill's job is
to route the decision to the right shape, then get the mechanical wiring
(numbering + two index updates + verification) right, which is where ADR
authoring actually slips.
The one empirical lever from the corpus audit
(docs/notes/20260605-adr-corpus-rubric-audit.md):
the corpus's only systematic drift is over-information, never thin.
So the recurring authoring mistake is writing too much for the stakes, not
too little. Bias toward brevity; let stakes earn length.
Step 0 — Does this even need an ADR?
An ADR records a decision with rationale and rejected alternatives, or a standing policy. It is not the home for:
- A mechanical change with no live alternatives (just do it; note in
CHANGELOG.md). - Behaviour the spec corpus (
docs/type-specification/,docs/internal-spec/) should own — when a change touches type-language behaviour or an analyzer contract, the spec binds; the ADR records why, not what. Put the normative rule in the spec, the rationale in the ADR. - A point-in-time measurement or survey — that is a
docs/notes/note (which an ADR may then cite as grounding).
If the decision is real but small and forced, it can still be an ADR — see the Mechanical archetype below. If there is no decision (no alternatives were weighed), it is probably a note or a CHANGELOG line, not an ADR.
Step 1 — Tag archetype + stakes (per ADR-49)
Before writing, fix the two tags ADR-49 defines. They decide which axes you must satisfy and how long the ADR may be.
- Archetype — Deliberative / Mechanical-policy / Evaluation-proposal. This sets which axes are core vs exempt.
- Stakes — low / mid / high, by reversibility × blast-radius × whether it touches the false-positive / soundness envelope. This sets the length budget (Step 3) and how hard the intent/criterion axes are read.
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.
- 11d ago First seen · 230 lines · 56 tokens per session scan A 979eac2677d5
rigor-adr-author is a skill published in the GitHub repository rigortype/rigor (107 stars, last pushed today), licensed MPL-2.0. It adds 56 tokens to every session and 2,830 once invoked, about $0.0002 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 2026-10-26.
rigor-adr-author compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rigor-adr-authorrigortype/rigor | Skill | 107 | today | MPL-2.0 | A | 56 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |