Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Contract Check

ASecurity

Validate an agent hand-off (Evidence Bundle, Root Cause, Design Spec, Implementation Report, Validation Report, Knowledge Entry) against its data contract before consuming it. Use at any pipeline seam to enforce LOCAL-reject ("escalate, don't guess") and the unforgeable-evidence rule (a PASS must carry test counts) instead of trusting prose. Triggers on "check the handoff", "is this evidence bundle complete", "verify the validation report", "contract check".

3 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentspythonrustgobash

Security Analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned 9/24/2026

$npx -y skills add OneDro1d/dark-factory --skill contract-check --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Contract Check?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Contract Check
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/onedro1d-contract-check/badge)](https://www.skillsdirectory.com/skills/onedro1d-contract-check)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: contract-check
description: Validate an agent hand-off (Evidence Bundle, Root Cause, Design Spec, Implementation Report, Validation Report, Knowledge Entry) against its data contract before consuming it. Use at any pipeline seam to enforce LOCAL-reject ("escalate, don't guess") and the unforgeable-evidence rule (a PASS must carry test counts) instead of trusting prose. Triggers on "check the handoff", "is this evidence bundle complete", "verify the validation report", "contract check".
allowed-tools: Read, Bash
---

# contract-check — reject incomplete hand-offs before you act on them

Goal: stop a malformed or under-evidenced hand-off from flowing downstream where
the next agent quietly copes — or guesses. This is the data-transform lens'
**LOCAL reject** rule and the promise-theory **unforgeable-evidence** rule, made
runnable. The contracts are defined in `.claude/context/AGENT-CONTRACTS.md`; this
skill runs the checker that mirrors them.

## When to run it
- A consuming agent receives an upstream artifact → check it **before** consuming.
  `REJECT` ⇒ kick back to the producer with the listed gaps; do not proceed.
- The orchestrator / a human reviews a `Validation Report` claiming PASS →
  confirm it carries test-count evidence (not "looks green").
- CI or a pre-commit hook wants a cheap structural gate on agent outputs.

## How to run it
```bash
# from repo root; reads a file or stdin
python3 .claude/skills/contract-check/check_contract.py <contract> path/to/artifact.txt

# contracts: evidence_bundle | root_cause | design_spec |
#            implementation_report | validation_report | knowledge_entry
```
Exit `0` + `OK` → consume. Exit `1` + `REJECT` → kick back; the output lists each
missing section and rule violation. Exit `2` → usage error.

## What each contract requires
See the table in `.claude/context/AGENT-CONTRACTS.md`. The rules with teeth:
- `evidence_bundle` / `root_cause` — must carry a real `file:line` citation.
- `validation_report` — `VERDICT` ∈ PASS|CONDITIONAL|FAIL, and a **PASS must
  carry test counts** (a bare "PASS" is UNVERIFIED → REJECT).
- `knowledge_entry` — must have an `F-###`/`D-###` id **and** a source.

## Maintaining it (the checker is itself test-first)
The checker is built RED→GREEN and guarded by tests:
```bash
python3 .claude/skills/contract-check/check_contract_test.py            # author suite
python3 .claude/skills/contract-check/check_contract_adversary_test.py  # blind adversary suite
```
If you add or change a contract: update `AGENT-CONTRACTS.md` (the source of
truth) **and** `check_contract.py` (its mirror), add a RED test first, keep both
suites green. No secrets/PII in fixtures.

Attribution

OneDro1dOneDro1d
View sourceSee grades on GitHubMore from OneDro1d →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →