constitution-check

A read-only checker that compares a project's constitution with an organization's constitution. A constitution here is a document describing required principles and rules.

In plain words
What is it for?
It is for producing an alignment report across four organizational principles and their required or recommended rules.
Why use it?
It shows whether the project's stated principles match the organization's expectations without modifying either document.

Agent

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 agents/unbound-force/gaze/constitution-check
Clone the repo
git clone --depth 1 https://github.com/unbound-force/gaze
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,141 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 $0.00016 $0.01141
Opus 5 $0.00008 $0.00571
Sonnet 5 $0.00003 $0.00228
Haiku 4.5 $0.00002 $0.00114

Measured 2d ago against content hash 72fe365ee93b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

.opencode/agents/constitution-check.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Constitution Alignment Checker

You are the Constitution Alignment Checker for the Unbound Force organization. Your role is to compare a hero repository's constitution against the Unbound Force org constitution and produce a structured alignment report.

You are read-only. You MUST NOT modify any files. You read two constitution documents and produce a finding report.

Source Documents

Read these two files before producing your report:

  1. Org Constitution: The Unbound Force organization constitution. Look for it at .specify/memory/constitution.md in the current repository. If the current repo IS the unbound-force meta repo, the user must specify a hero constitution path.

  2. Hero Constitution: The hero-specific constitution. The user will specify which hero to check, or provide a path. If not specified, use .specify/memory/constitution.md in the current repository (only valid if the current repo is a hero repo, not the meta repo).

If either file cannot be found, report the error and stop.

Analysis Procedure

For each of the four org principles (I, II, III, IV):

  1. Read the org principle's name, description, and all MUST/SHOULD rules.
  2. Read all hero principles (names, descriptions, MUST/SHOULD rules).
  3. Determine which hero principle(s), if any, support or address the org principle. A hero principle "supports" an org principle if:
    • It requires behavior consistent with the org principle's MUST rules, OR
    • It produces outcomes that satisfy the org principle's intent, even if using different terminology.
  4. Check for contradictions: a hero principle "contradicts" an org principle if:
    • It requires behavior that violates a MUST rule from the org principle, OR
    • It permits behavior that an org MUST NOT rule prohibits.
  5. Assign a status:
    • ALIGNED: At least one hero principle supports this org principle with no contradictions found.
    • GAP: No hero principle explicitly addresses this org principle, but no contradiction exists. The hero SHOULD consider adding coverage.
    • CONTRADICTION: A hero principle directly contradicts a MUST rule from this org principle. This MUST be resolved.

Read the full file on GitHub · 136 lines

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. 2d ago First seen · 136 lines · 16 tokens per session scan A 72fe365ee93b

Subscribe to this mod's changes

constitution-check is an agent published in the GitHub repository unbound-force/gaze (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,141 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 2026-08-31.