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-clarify)<a href="https://agentmods.dev/commands/niels-emmer/myace/sdd-clarify"><img src="https://agentmods.dev/badge/commands/niels-emmer/myace/sdd-clarify/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-clarify"><img src="https://agentmods.dev/badge/commands/niels-emmer/myace/sdd-clarify.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 | $0.00025 | $0.00372 |
| Opus 5.5 | $0.00010 | $0.00149 |
| Sonnet 5.5 | $0.00005 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
sdd-clarify 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 1mo 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 the target
docs/specs/<slug>/spec.md. - Check it against these categories for gaps, not just the markers already flagged: functional scope boundaries, data model and ownership, UX/error-state flows, non-functional constraints (performance, scale, availability), external integrations, edge cases, explicit exclusions, terminology consistency, and what "done" means. A spec can look complete and still be silently missing one of these.
- Rank every open question — flagged or newly found — by how much it would change the plan if answered differently. Keep only the top five; lower-impact ones get a reasonable default noted in the spec instead of a question.
- Ask one question at a time, each answerable in a short phrase or a multiple-choice pick, with your own recommended answer stated up front so the user is confirming or correcting, not starting from a blank page.
- After each answer, immediately write it into the relevant spec section (not a separate changelog) and remove the corresponding
[NEEDS CLARIFICATION]marker — don't batch edits until the end, since a session that gets cut short should still leave the spec more resolved than it started. - Stop once every top-five question is resolved or explicitly deferred with a stated default. Don't manufacture additional questions to seem thorough.
- Report the updated spec's remaining open items, if any, and state plainly whether it's ready for
sdd-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.
- 1mo ago First seen · 14 lines · 25 tokens per session scan A 0ffcbd2fb52b
sdd-clarify is a command published in the GitHub repository niels-emmer/myace (1 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 372 once invoked, about $0.0001 per session on Opus 5.5. 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
distill
Distill important session insights into doc/loom/knowledge.
address
Address the pressure-test review for a plan.
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.