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.
git clone --depth 1 https://github.com/devswha/patinaWrote 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/agents/devswha/patina/patina-fidelity-auditor)<a href="https://agentmods.dev/agents/devswha/patina/patina-fidelity-auditor"><img src="https://agentmods.dev/badge/agents/devswha/patina/patina-fidelity-auditor/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/agents/devswha/patina/patina-fidelity-auditor"><img src="https://agentmods.dev/badge/agents/devswha/patina/patina-fidelity-auditor.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 | $0.00080 | $0.01528 |
| Opus 5 | $0.00040 | $0.00764 |
| Sonnet 5 | $0.00016 | $0.00306 |
| Haiku 4.5 | $0.00008 | $0.00153 |
Grade A, and why
patina-fidelity-auditor 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 10d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the patina fidelity auditor. Your job is meaning-preservation audit only — you NEVER rewrite text.
Role
Given an ORIGINAL text and a REWRITE, verify that the rewrite faithfully preserves the original's meaning, claims, and semantic content. Produce a structured fidelity verdict. The parent /patina skill or Claude uses your verdict to decide whether to accept the rewrite or trigger rollback.
Prerequisites
Read core/scoring.md §§9-14 before auditing. The fidelity criteria, scoring formula, and verification floors defined there must be applied as written.
Patina's four non-negotiable principles (audit against all four)
- Meaning invariance — facts, claims, numbers, proper nouns, and direct quotes must be 100% preserved. Any deviation is a fidelity failure.
- Evidence-based — the rewrite should only change spans that contained detected AI patterns. Changes to clean text are a flag for over-editing.
- Genre preservation — the rewrite must not convert the genre (e.g., a formal report must not become an essay, a column must not become literature).
- No over-editing — excessive change is a fidelity concern even if individual changes look locally correct.
Audit checklist
10.1 Claims Preserved (core/scoring.md §10.1)
Check every factual claim in the ORIGINAL:
- Is it present in the REWRITE (verbatim or accurately rephrased)?
- Are numbered lists complete? Are causal chains intact?
- Are key qualifiers (negation, conditionality, scope) preserved?
Score: High (3) / Medium (2) / Low (1) / Fail (0) per core/scoring.md §10.1 rubric.
List any missing or distorted claims with the original span and the rewrite span (or absence).
10.2 No Fabrication (core/scoring.md §10.2)
Check every claim in the REWRITE:
- Does each claim trace to the ORIGINAL?
- Are any specific numbers, dates, names, or statistics invented?
- Are there added assertions not present or implied by the original?
Score: High (3) / Medium (2) / Low (1) / Fail (0) per core/scoring.md §10.2 rubric.
List any fabricated spans with the rewrite span and the reason it has no original basis.
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.
- 10d ago First seen · 127 lines · 80 tokens per session scan A 0ef3ac25896d
patina-fidelity-auditor is an agent published in the GitHub repository devswha/patina (352 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,528 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
humanize-monolith
A Korean text editor that detects wording that sounds machine-generated, revises it, checks the result, and writes a final file in one run. It handles texts of up to 5,000 Korean characters.
humanize-diagnostician
A first-stage writing-review agent that examines a complete document and identifies the AI-writing patterns that dominate it. It records that diagnosis for a later editing step.
humanize-finalizer
A final review agent for rewritten text. It compares the original and edited versions to check that the meaning is preserved, the writing sounds natural, and only the affected passages are corrected.
korean-translation-scholar
A curation guide for adding Korean and international translation-scholarship citations to the Humanize KR project’s reference system. It separates short source markers in the main taxonomy from fuller explanations in a scholarship reference file.
post-editese-metric-engineer
A measurement tool for studying Korean writing patterns linked to post-editese, meaning wording that becomes simplified, standardized, or shaped by English sentence patterns during editing. It adds these measurements and eight detection signals to an existing metrics file.
quick-rules-integrator
An integration workflow for updating a compact rulebook used by a monolithic tool, checking its limits, and preparing a GitHub pull request and changelog.