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.
npx skills add evanmcgoogan/skin-in-the-game --skill constitution-checkgit clone --depth 1 https://github.com/evanmcgoogan/skin-in-the-gameWrote 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/skills/evanmcgoogan/skin-in-the-game/constitution-check)<a href="https://agentmods.dev/skills/evanmcgoogan/skin-in-the-game/constitution-check"><img src="https://agentmods.dev/badge/skills/evanmcgoogan/skin-in-the-game/constitution-check/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/skills/evanmcgoogan/skin-in-the-game/constitution-check"><img src="https://agentmods.dev/badge/skills/evanmcgoogan/skin-in-the-game/constitution-check.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 | $0.00103 | $0.00609 |
| Opus 5 | $0.00051 | $0.00304 |
| Sonnet 5 | $0.00021 | $0.00122 |
| Haiku 4.5 | $0.00010 | $0.00061 |
Grade A, and why
constitution-check 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.
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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constitution Check
A constitution that isn't checked is decoration. This skill is the enforcement gate: it reviews a concrete plan or diff against the twelve principles and flags real violations before they ship. It fires at two moments — after a plan is drafted, before you build it, and before you call a build done.
Read PRINCIPLES.md at the plugin root for the twelve, then review the work in front of you against each. Be concrete: a principle you can't point at a specific line or choice for is a principle you can't enforce.
How to run the check
Go principle by principle. For each, decide: does this plan/diff honor it, violate it, or not apply?
- 0 · Operating Contract — Am I about to escalate something I should own, or own something I should escalate?
- 1 Amplify / own — Am I handing the human work they shouldn't have to bless?
- 2 Different plane · 3 Durable thesis — Does this serve the durable goal, or just a local win?
- 4 Reality-graded · 5 Honesty — Is every claim of success something I actually verified? Any vanity metric? Any fake pass?
- 6 Grill · 7 Delete — Is there an unresolved CEO-line decision I'm assuming through? A requirement here I should delete rather than build?
- 8 Research · 9 Build-on-top · 10 Density · 11 Clean — Did I read before writing? Am I co-opting the cleanest substrate or hand-rolling? Am I diluting scope? Is this clean, or a Frankenstein patch?
Output format
Report only what's load-bearing:
Constitution Check
✅ Honored: <principles that clearly pass — one line>
⚠️ Violations:
- P<n> <name>: <the specific line/choice that violates it> → <recommended fix>
🚪 Escalate: <any CEO-line decision surfaced by P6/P7 that needs the human>
If there are no violations, say so plainly — do not manufacture findings to look thorough (that would itself violate Principle 5). A clean plan is a clean plan.
The test
Every principle must be checkable against something concrete in the plan or diff. If you can't point to the line, you can't enforce the principle — sharpen the principle or sharpen the plan.
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.
- 11d ago First seen · 37 lines · 103 tokens per session scan A dc9c2c8198ca
constitution-check is a skill published in the GitHub repository evanmcgoogan/skin-in-the-game (1 stars, last pushed 3mo ago), licensed MIT. It adds 103 tokens to every session and 609 once invoked, about $0.0005 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.
Other skills, from other repositories
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
code-review
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
goal-plan-clean
A guide for creating a reusable plan-review loop. It repeatedly checks a plan, fixes blocking issues and suggestions, and stops after approval or a small number of review rounds.
loop-test
A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.
create-task
This skill should be used when creating a task in the active tracker - "create task", "create issue", "bd create", "new task", "add task", "add issue". Ensures all required fields are provided, enforces English-only task content, and suggests epic labels. Triggers on any task creation in any context - commands…