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-add-reference/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-add-reference)<a href="https://agentmods.dev/skills/rigortype/rigor/rigor-add-reference"><img src="https://agentmods.dev/badge/skills/rigortype/rigor/rigor-add-reference/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-add-reference"><img src="https://agentmods.dev/badge/skills/rigortype/rigor/rigor-add-reference.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 | $0.00047 | $0.02083 |
| Opus 5.5 | $0.00019 | $0.00833 |
| Sonnet 5.5 | $0.00009 | $0.00417 |
| Haiku 4.5 | $0.00005 | $0.00208 |
Grade C, and why
rigor-add-reference 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| Orphaned `.git/modules/<name>/` (no longer in `.gitmodules`) | `rm -rf .git/modules/<name>` after confirming nothing references it | How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a Reference Submodule
Use this skill when the user wants to add a new upstream repo under references/. The change always touches three things together: .gitmodules (via git submodule add), Makefile (REFERENCE_SUBMODULES list + init-submodules body), and the submodule pointer commit. They belong in a single commit.
The standing rule is in AGENTS.md: these submodules are read-only reference material, not Rigor code — never require, import, or copy upstream implementation into product code; read the behaviour, then implement the smallest Rigor-side equivalent. Update a submodule only when intentionally changing the referenced revision.
The catalog — what each tree is for
| Submodule | Upstream | Use |
|---|---|---|
references/rbs |
https://github.com/ruby/rbs.git |
RBS syntax, stdlib signatures, test cases, implementation behaviour. The compatibility target for the RBS ecosystem. |
references/python-typing |
https://github.com/python/typing.git |
Written-down Python typing concepts (gradual typing, generics, protocols, variance), borrowed by idea only. Not a syntax compatibility target. |
references/ruby |
https://github.com/ruby/ruby.git (branch ruby_4_0) |
Ruby interpreter source. Parsed offline to derive the PHPStan-functionMap-style catalog of built-in methods: argument / return types plus per-method effect facets (pure, self-mutating, block-dependent). Never link Rigor runtime code against it. |
references/typeprof |
https://github.com/ruby/typeprof.git |
TypeProf source — the reference implementation of Ruby type inference. Read for ideas and behaviour comparisons; never import or require it. |
The trees are large, so the root .ignore lists /references/ to keep rg out by default (git is unaffected). Search one intentionally, and scope the path so you do not pull in vendor/:
rg PATTERN --no-ignore references/rbs
Step 0 — Decide the checkout strategy
Before running any command, ask (or infer from context) whether a sparse checkout is needed:
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 · 158 lines · 47 tokens per session scan C 9df67204d4cd
rigor-add-reference is a skill published in the GitHub repository rigortype/rigor (107 stars, last pushed today), licensed MPL-2.0. It adds 47 tokens to every session and 2,083 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
rigor-add-reference compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rigor-add-referencerigortype/rigor | Skill | 107 | today | MPL-2.0 | C | 47 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 83k | 5d ago | MIT | A | 46 | Claude Code |
| prowler-commitprowler-cloud/prowler | Skill | 15k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| gh-auth-isolationgithub/gh-aw | Skill | 5.6k | today | MIT | A | 20 | Claude Code, Codex |
| github-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 51 | Claude Code |
| comet-githubrpamis/comet | Skill | 3.3k | today | MIT | A | 72 | Claude Code, Codex |
| release-helperSahir619/fable-method | Skill | 2.3k | 1mo ago | MIT | A | 43 | Claude Code |