skill-contract-reviewer

skill-contract-reviewer is a skill for Claude Code, Codex from rohitg00/ai-engineering-from-scratch. It costs 24 tokens per session (381 once invoked), scanned A, original, MIT.

A reviewer for proposed Agent Skill packages, which are reusable instruction bundles for AI agents. It checks the package contract and determines whether the work should be an instruction set, an external capability, a lifecycle step, deterministic logic, or isolated delegation.

In plain words
What is it for?
Use it to validate a proposed skill directory, run its checker, classify the workflow, and choose the smallest suitable set of reusable building blocks.
Why use it?
It prevents workflows from being packaged in the wrong form and catches contract errors before implementation. It also separates portable skill behavior from features supplied by a particular host.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to validate a proposed skill directory, run its checker, classify the workflow, and choose the smallest suitable set of reusable building blocks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rohitg00/ai-engineering-from-scratch/skill-contract-reviewer
About the project

AI Engineering from Scratch is a free, open-source curriculum that teaches people to build AI systems through lessons and reusable artifacts such as prompts, skills, agents, and MCP servers. It is for learners who want practical foundations or want to create AI applications, and the catalogue skills support parts of that curriculum.

rohitg00/ai-engineering-from-scratch · 54,035 stars · on GitHub · aiengineeringfromscratch.com

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.

Any agent
npx skills add rohitg00/ai-engineering-from-scratch --skill skill-contract-reviewer
Clone the repo
git clone --depth 1 https://github.com/rohitg00/ai-engineering-from-scratch

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 skill-contract-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/rohitg00/ai-engineering-from-scratch/skill-contract-reviewer/github.svg)](https://agentmods.dev/skills/rohitg00/ai-engineering-from-scratch/skill-contract-reviewer)
Your own site
<a href="https://agentmods.dev/skills/rohitg00/ai-engineering-from-scratch/skill-contract-reviewer"><img src="https://agentmods.dev/badge/skills/rohitg00/ai-engineering-from-scratch/skill-contract-reviewer/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.

agentmods 80×15 button for skill-contract-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/rohitg00/ai-engineering-from-scratch/skill-contract-reviewer"><img src="https://agentmods.dev/badge/skills/rohitg00/ai-engineering-from-scratch/skill-contract-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 381 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00024 $0.00381
Opus 5 $0.00012 $0.00191
Sonnet 5 $0.00005 $0.00076
Haiku 4.5 $0.00002 $0.00038

Measured 11d ago against content hash 84345705cb49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skill-contract-reviewer 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_skill.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

phases/13-tools-and-protocols/22-skills-and-agent-sdks/outputs/skill-contract-reviewer/SKILL.md · 38 lines

What it actually says

Skill contract reviewer

Use this skill when a workflow is about to become a reusable agent artifact.

  1. Set SKILL_ROOT to the absolute directory containing this installed SKILL.md. Do not assume the process working directory is the bundle.
  2. Set TARGET_ROOT to the absolute original workspace working directory and resolve the proposed skill directory under that root.
  3. Read $SKILL_ROOT/references/contract.md and validate the portable SKILL.md identity fields.
  4. Read $SKILL_ROOT/references/decision-model.md and separate repository context, reusable method, external capability, lifecycle timing, deterministic logic, and isolated delegation.
  5. Before execution, show the exact resolved argument vector. Run python3 "$SKILL_ROOT/scripts/check_skill.py" "$TARGET_SKILL", where TARGET_SKILL is the absolute proposed skill directory under TARGET_ROOT.
  6. Inspect the JSON report. Fix every error before discussing host-specific extensions.
  7. Compare the proposed artifact with $SKILL_ROOT/assets/task-shapes.json and return the smallest composable set of primitives.

Do not claim that a runtime extension is part of the portable contract. Do not treat a valid skill as permission to run scripts or access tools.

Return the validation report, the selected primitives, and one sentence explaining each selection. Include execution evidence with the resolved script path, resolved target path, cwd, exact argv, and exit code. If the host cannot expose one of those observations, mark it unverified instead of inventing it.

Files

What ships with it

4 files 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.

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. 11d ago First seen · 38 lines · 24 tokens per session scan A 84345705cb49

Subscribe to this mod's changes

skill-contract-reviewer is a skill published in the GitHub repository rohitg00/ai-engineering-from-scratch (54,035 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 381 once invoked, about $0.0001 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.