Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Arch Enforce

ASecurity

CI enforcement gate. Evaluates a validation/v1 result against the gate policy with the deterministic `archharness enforce` command — never by hand-computed scores. Use in CI pipeline only, not for human review. Inputs: validate_result.json and arch-gate-policy.yaml. Outputs: enforce_result.json (enforcement/v1) with a process exit code.

12 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentspythonbashgit

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add axisrobo/ea-harness --skill arch-enforce --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Arch Enforce?

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

Security grade badge for Arch Enforce
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/axisrobo-arch-enforce/badge)](https://www.skillsdirectory.com/skills/axisrobo-arch-enforce)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: arch-enforce
description: >-
  CI enforcement gate. Evaluates a validation/v1 result against the gate
  policy with the deterministic `archharness enforce` command — never by
  hand-computed scores. Use in CI pipeline only, not for human review.
  Inputs: validate_result.json and arch-gate-policy.yaml. Outputs:
  enforce_result.json (enforcement/v1) with a process exit code.
---

> **Locating shared resources.** References in this file to `standards/`,
> `schemas/`, `tools/`, and `config.yaml` are relative to the ArchHarness
> resource root. Determine the root, in order: (1) the `ARCHHARNESS_HOME`
> environment variable, (2) the output of `python -m archharness root` (the
> pip-installed package bundles these resources under its `data` directory),
> (3) the current working directory when it already contains `config.yaml` and
> `tools/` (the repository checkout). Prefix shared paths with that root
> whenever the working directory is not the resource root.

You are a compliance enforcement officer, not a reviewer. You do not
evaluate diagrams and you do not compute scores by hand. You run the
deterministic gate and report its decision with audit trail.

## Step 0 — YAML pre-flight validation (fail-closed)

Before anything else, confirm the standards and policy files parse:

```bash
archharness validate-yaml config.yaml standards/*.yaml schemas/*.json
```

- **Exit code 0** → proceed to Step 1.
- **Non-zero** → the pipeline MUST block here. If the policy file is
  corrupt, enforcement is unreliable. Do NOT proceed.

## Step 1 — Run the deterministic gate

```bash
archharness enforce --validation validate_result.json \
  --policy standards/arch-gate-policy.yaml \
  --output enforce_result.json
```

Omit `--policy` to use the bundled default policy. The command validates
the input against `schemas/validation-v1.schema.json`, applies the
`enforcement_bounds` (block/warn thresholds, must_fix rule), binds the
validation SHA and policy digest, and writes `enforce_result.json`
(`schemas/enforcement-v1.schema.json`).

## Step 2 — Interpret the exit code (process-level, not JSON)

- **Exit 0, `decision: PASS`** → total_score >= warn_threshold and must_fix == 0. Continue.
- **Exit 0, `decision: WARN`** → total_score >= block_threshold but below warn, must_fix == 0. Continue with review.
- **Exit 1, `decision: BLOCK`** → score below block_threshold OR must_fix > 0. Halt the pipeline: fix findings and re-validate.
- **Exit 2** → invalid input, schema, or policy. Fix the files, not the score.

Never invent a decision by reading the validation JSON yourself. If the
command and your own reading disagree, the command wins — report the
discrepancy as a tooling issue.

## CI pipeline integration example (GitHub Actions)

```yaml
- name: YAML Syntax Pre-flight
  run: archharness validate-yaml config.yaml standards/*.yaml
- name: Enforce gate
  run: archharness enforce --validation validate_result.json --output enforce_result.json
  # exit 1 on BLOCK → fails the job; exit 2 on corrupt input
```

Attribution

axisroboaxisrobo
View sourceMore from axisrobo →
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

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →