create-rationale-contract

create-rationale-contract is a skill for Claude Code, Codex from rosselps/whyguard. It costs 47 tokens per session (551 once invoked), scanned A, original, MIT.

A written record of a confirmed code rule, stored in a YAML file with its reason, evidence, tests, owners, and expiry conditions.

In plain words
What is it for?
Use it after reviewing a WhyGuard finding to document the files and symbols it protects, the behavior that must remain, supporting issues or pull requests, and the tests required.
Why use it?
It prevents future developers or coding agents from having to rediscover why the rule exists. It also separates a human-approved decision from an unverified suggestion.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/rosselps/whyguard/create-rationale-contract
Any agent
npx skills add rosselps/whyguard --skill create-rationale-contract
Clone the repo
git clone --depth 1 https://github.com/rosselps/whyguard

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for create-rationale-contract

README.md
[![agentmods](https://agentmods.dev/badge/skills/rosselps/whyguard/create-rationale-contract.svg)](https://agentmods.dev/skills/rosselps/whyguard/create-rationale-contract)
Your own site
<a href="https://agentmods.dev/skills/rosselps/whyguard/create-rationale-contract"><img src="https://agentmods.dev/badge/skills/rosselps/whyguard/create-rationale-contract.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 551 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00047 $0.00551
Opus 5 $0.00023 $0.00275
Sonnet 5 $0.00009 $0.00110
Haiku 4.5 $0.00005 $0.00055

Measured 3d ago against content hash 83d83750b158, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-rationale-contract 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 3d 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.

.kiro/skills/create-rationale-contract/SKILL.md · 55 lines

What it actually says

When to use this skill

After a Finding's protected property has been reviewed and confirmed by a human (not just proposed by the deterministic scan), capture it as a durable rationale contract so the next agent or reviewer does not have to re-trace the same history.

Workflow

  1. Confirm the finding has moved from proposed to confirmed state (see .kiro/steering/evidence-policy.md) with a human actor recorded.
  2. Create a new file at .whyguard/decisions/<short-slug>.yml following this shape:
    id: <short-slug>
    version: 1
    status: active
    scope:
      files:
        - <path/to/file.ts>
      symbols:
        - <symbolName>
    reason: >
      <one or two sentences describing the real-world incident or requirement>
    must_preserve:
      - <explicit behavioral property, phrased as an invariant>
    evidence:
      - type: issue
        id: "<number>"
      - type: pull_request
        id: "<number>"
    required_tests:
      - <path/to/regression-test>
    expires_when:
      - <condition under which this decision no longer applies>
    owners:
      - <team-or-individual>
    
  3. Do not mark status: active unless a human has actually confirmed the property; if in doubt, leave it as a draft and ask.
  4. Link the contract's id back to the originating finding for traceability.
  5. If a decision is later superseded, set status: replaced or status: expired — do not delete the file; history matters as much for decisions as for code.

Anti-patterns to avoid

  • Auto-generating a rationale contract straight from an unconfirmed proposed finding.
  • Writing a vague must_preserve statement (e.g., "keep it safe") instead of a checkable invariant (e.g., "one idempotency key creates at most one order").
  • Omitting evidence — a contract without evidence IDs cannot be audited later.
Changes

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.

  1. 3d ago First seen · 55 lines · 47 tokens per session scan A 83d83750b158

Subscribe to this mod's changes

create-rationale-contract is a skill published in the GitHub repository rosselps/whyguard (0 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 551 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 2026-08-31.

Related

Other skills, from other repositories

analyzing-packed-malware-with-upx-unpacker

Identifies and unpacks UPX-packed malware samples, including binaries with modified UPX magic bytes or headers that block automated decompression, to recover the original executable for static analysis. Use when a sample shows high entropy, minimal imports, or only LoadLibrary/GetProcAddress in its import table, or…

mukul975/Anthropic-Cybersecurity-Skills · 88 tokens

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects. Use when triaging a suspicious PDF attachment from a phishing email, analyzing a PDF-based exploit document, or building detection signatures for weaponized PDF…

mukul975/Anthropic-Cybersecurity-Skills · 73 tokens

analyzing-android-malware-with-apktool

Perform static analysis of Android APK malware using apktool for resource decompilation, jadx for Java source recovery, and androguard for manifest inspection, dangerous permission-combination detection, and identification of obfuscated code, dynamic code loading, and reflection-based API calls. Use to statically…

mukul975/Anthropic-Cybersecurity-Skills · 84 tokens

cli-analysis

Run the pyscn command-line tool for Python code quality analysis - CI/CD quality gates, HTML/JSON/CSV reports, full analysis runs, and project configuration. Use when user wants a CI check, a shareable report file, or to configure pyscn for a project.

ludo-technologies/pyscn · 59 tokens

health-check

Get an overall Python code quality health score using pyscn. Use when user asks how healthy or good the code is, wants a quality overview, a grade, a summary of technical debt, or a before/after quality comparison.

ludo-technologies/pyscn · 49 tokens

architecture-review

Analyze Python module architecture using pyscn - class coupling (CBO), cohesion (LCOM), dependency cycles, and module communities. Use when user asks about architecture, module structure, coupling, circular dependencies, or which files to review or change together.

ludo-technologies/pyscn · 53 tokens