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/nicelight/DevRails-26Wrote 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/nicelight/devrails-26/kiss-architect)<a href="https://agentmods.dev/commands/nicelight/devrails-26/kiss-architect"><img src="https://agentmods.dev/badge/commands/nicelight/devrails-26/kiss-architect/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/nicelight/devrails-26/kiss-architect"><img src="https://agentmods.dev/badge/commands/nicelight/devrails-26/kiss-architect.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 | $0.00026 | $0.00560 |
| Opus 5 | $0.00013 | $0.00280 |
| Sonnet 5 | $0.00005 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
kiss-architect 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 9d 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
/kiss-architect - Architect proposal preflight
Ensure that every architecture finding, design element, or proposed correction entering an operator response or canonical artifact has passed the Architect proposal preflight.
<input_contract> Read:
AGENTS.md;.memory-bank/roles/architect.md;- the current request and supplied proposals;
- the active skill contract when present;
- accepted requirements, decisions, specifications, and current-state evidence required by the proposal's consequence surface.
If the deployed role contract is missing, stop and request coherent framework bootstrap or sync. </input_contract>
<hard_invariants>
- Keep the active role, scope, permissions, and mutation authority unchanged.
- The active skill retains ownership of its inputs, coverage, artifacts, statuses, gates, validation, and handoff.
- Neither this skill nor its findings create target authority.
- Modify canonical architecture or specifications only through their installed owning skill.
- Do not copy the Architect policy into another artifact. </hard_invariants>
When evaluating a correction to an existing proposal, reassess the correction across its consequence surface instead of treating it as an isolated patch.
Revise, simplify, defer, or reject candidates that do not survive the value-versus-cost assessment before they enter the response or canonical design.
<agent_discretion> Choose the research order, tools, probes, candidate grouping, and evidence depth within the Architect role and active skill contract. </agent_discretion>
<required_outputs> Return only preflighted architecture conclusions, material trade-offs, remaining risks, and operator decisions using the communication contract defined by the Architect role.
The active skill may require additional output fields or artifacts. Create no durable artifact unless the active owning skill requires it. </required_outputs>
- every material candidate entering the result has passed the Architect proposal preflight;
- every material implementation, cost, fragility, regression, and operational factor affects the final recommendation;
- no correction was evaluated only as a local patch;
- the active skill contract remains satisfied.
<handoff_contract> Return the result to the active workflow.
If accepted canonical changes are requested without an active owning skill, continue only through the installed skill that owns those artifacts. </handoff_contract>
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.
- 9d ago First seen · 83 lines · 26 tokens per session scan A 8432fff3715c
kiss-architect is a command published in the GitHub repository nicelight/DevRails-26 (22 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 560 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 2026-08-30.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.