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-prior-art/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-prior-art)<a href="https://agentmods.dev/skills/rigortype/rigor/rigor-prior-art"><img src="https://agentmods.dev/badge/skills/rigortype/rigor/rigor-prior-art/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-prior-art"><img src="https://agentmods.dev/badge/skills/rigortype/rigor/rigor-prior-art.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 | $0.00055 | $0.01919 |
| Opus 5.5 | $0.00022 | $0.00768 |
| Sonnet 5.5 | $0.00011 | $0.00384 |
| Haiku 4.5 | $0.00006 | $0.00192 |
Grade A, and why
rigor-prior-art 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rigor-prior-art — corpus archaeology with citation-grade output
The rigor repository accumulates evidence across 80+ ADRs, 100+ research notes, the CHANGELOG and its archives, a handbook, and a manual. Answering "what do we already know about X?" is a recurring task whose cost is dominated by two things this skill freezes: knowing where each kind of evidence lives, and the discipline that keeps citations accurate. The stakes are asymmetric — a published overclaim ("Steep misses X", "we measured Y") gets challenged by experts and costs credibility, so a finding you cannot pin to a file and line is not a finding.
When NOT to use this
A single fact in a file you already know → just Read/rg it directly.
This skill is for topic-level sweeps ("everything the corpus says about
X") and for claims that need verified citations before they leave the
repo (talks, comparisons, READMEs).
Corpus map — where evidence lives
| Location | What lives there | When to look |
|---|---|---|
docs/adr/README.md |
Canonical ADR index: title + a short status (Accepted (WD1–WD4 landed; WD5 deferred)). Index only — no detail, by ADR-97. |
First stop, to shortlist 2–5 ADRs and to see which are live. Never a source for what was decided. |
AGENTS.md ADR premises |
A capped premise set (≤12) — topic and link, no status (ADR-97). | Which few ADRs bind every task. Never a source. |
docs/notes/README.md |
Categorized note index: library surveys / coverage audits / regression sweeps / teeth / outside-research reviews / perf / meta. | Shortlisting notes by category. |
docs/adr/*.md |
Full decisions: criteria, rejected alternatives, gate results. | The "why" behind a behaviour; what was rejected and why. |
docs/notes/*.md |
What was observed, when, against which Rigor version. | Measurements, sweeps, adjudications. |
docs/CHANGELOG-*.md + CHANGELOG.md |
Per-feature landing narratives with spec/corpus evidence. | Comparative evidence often lives ONLY here — e.g. the rbs_rails coverage comparison and the ~20-methods-per-column contrast are in the 0.1.x archive, indexed nowhere else. Always include every archive. |
docs/design/*.md |
Design plans that preceded ADRs. | Pre-decision context, roadmaps. |
docs/handbook/, docs/manual/ |
User-facing claims. | What Rigor promises publicly — the bar a new claim must clear. |
docs/notes/deep-research/ |
External LLM deep-research reports stored for reference. | Community/competitor landscape only — never a first-party claim (register rules in its README). |
references/ submodules |
Vendored upstream source (read-only). | Verifying a claim about another tool's code. |
git log -S"term" |
When a claim or feature landed. | Dating evidence; finding the landing commit. |
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.
- 11d ago First seen · 120 lines · 55 tokens per session scan A 644d5abe6fd5
rigor-prior-art is a skill published in the GitHub repository rigortype/rigor (107 stars, last pushed today), licensed MPL-2.0. It adds 55 tokens to every session and 1,919 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-prior-art compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rigor-prior-artrigortype/rigor | Skill | 107 | today | MPL-2.0 | A | 55 | 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 |