Borrowing it
Nothing to install: this file belongs to adrian-d-hidalgo/nestjs-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adrian-d-hidalgo/nestjs-mcp-server/main/.claude/commands/constitution.mdgit clone --depth 1 https://github.com/adrian-d-hidalgo/nestjs-mcp-serverWrote 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/commands/adrian-d-hidalgo/nestjs-mcp-server/constitution)<a href="https://agentmods.dev/commands/adrian-d-hidalgo/nestjs-mcp-server/constitution"><img src="https://agentmods.dev/badge/commands/adrian-d-hidalgo/nestjs-mcp-server/constitution.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.01909 |
| Opus 5 | $0.00030 | $0.00955 |
| Sonnet 5 | $0.00012 | $0.00382 |
| Haiku 4.5 | $0.00006 | $0.00191 |
Grade A, and why
constitution 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 8d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This command produces an issue and nothing else. Issue creation stays high-level: the technical
SPEC (code, approach, the Public API and SemVer calls) is authored later by /specification. You
load the github-issues skill for the modes, labels, templates, duplicate check, and the
authorization contract — you never fork its rules.
Always propose; never create without explicit authorization.
Routes 4 and 5 are the pair most often confused. The test: does something already exist and
behave wrongly (→ /debug), or does something not exist yet (→ Route B)? "The retry logic is
wrong" is a bug; "there is no retry logic" is a capability.
Once met, continue and propose. Anything the source leaves unresolved (an exact option name, a default value) is carried as an acceptance criterion to verify, not invented as a fact. For anything unclear, ask; never invent scope, coverage, a relationship, or the closure condition.
Maturity gate. A requirement too vague to derive verifiable acceptance criteria from is not a requirement yet — STOP and ask the specific question that would make it one. Never invent the missing layer to produce a well-formed issue: a well-formed issue built on an invented premise is worse than no issue, because it looks decided.
Code inspection is allowed and often required — for a technical task (Mode T) or a refactor
(Mode R), the truth of the current state lives in the code. Use codegraph. But the file-level
approach still belongs to /specification, not here.
Route B — the requirement (free text, or the content of a discussion) → ONE issue.
-
Understand the work. State the real current state → target state → why at the requirement level. For Mode T / Mode R, read the actual code with codegraph to state the current state accurately — never from memory.
-
Duplicate check FIRST, before drafting. Run the
github-issuesskill's duplicate-check query, open and closed. Drafting before checking wastes the draft and biases you toward creating it. On any plausible match → the conflict gate (step 5).
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.
- 8d ago First seen · 116 lines · 59 tokens per session scan A 6cadbb114c1c
constitution is a command published in the GitHub repository adrian-d-hidalgo/nestjs-mcp-server (38 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,909 once invoked, about $0.0003 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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.