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.
git clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/sdd-constitution)<a href="https://agentmods.dev/commands/niels-emmer/myace/sdd-constitution"><img src="https://agentmods.dev/badge/commands/niels-emmer/myace/sdd-constitution/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/commands/niels-emmer/myace/sdd-constitution"><img src="https://agentmods.dev/badge/commands/niels-emmer/myace/sdd-constitution.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 | $0.00031 | $0.00383 |
| Opus 5 | $0.00015 | $0.00192 |
| Sonnet 5 | $0.00006 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
sdd-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 5d 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.
What it actually says
- Read
docs/constitution.mdif it exists; otherwise this is a first-time setup. - Gather principles from the user's request and, on first setup, from the codebase itself — recurring invariants already enforced in code or docs (e.g., an existing "never hard-delete user data" rule) are candidates for promotion to a constitution principle, not just a comment.
- Write each principle as a short, checkable MUST/SHOULD statement with a one-line rationale — not a vague value statement. "All external API responses MUST be versioned" is checkable; "we care about API stability" is not.
- Keep the set small — five to ten principles. A constitution that tries to cover everything stops functioning as a filter; it should list the things that are expensive to get wrong and easy to accidentally violate.
- Version the document: bump the major segment on a principle removed or redefined, minor on a principle added, patch on a wording clarification with no behavioral change. Record the bump and what changed at the top of the file.
- Save to
docs/constitution.md. This is a different document fromAGENTS.md— it governs what the product is allowed to do, not how an agent behaves while working in the repo. - Report which principles were added, changed, or removed, so the user can catch an unintended change before it becomes the standard every future spec is checked against.
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.
- 5d ago First seen · 14 lines · 31 tokens per session scan A 54e46f74a6cd
sdd-constitution is a command published in the GitHub repository niels-emmer/myace (1 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 383 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
address
Address the pressure-test review for a plan.
distill
Distill important session insights into doc/loom/knowledge.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.