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.
npx skills add Hmbown/knightsradiant --skill choose-ordergit clone --depth 1 https://github.com/Hmbown/knightsradiantWrote 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/skills/hmbown/knightsradiant/choose-order)<a href="https://agentmods.dev/skills/hmbown/knightsradiant/choose-order"><img src="https://agentmods.dev/badge/skills/hmbown/knightsradiant/choose-order/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/skills/hmbown/knightsradiant/choose-order"><img src="https://agentmods.dev/badge/skills/hmbown/knightsradiant/choose-order.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 | $0.00017 | $0.00525 |
| Opus 5 | $0.00009 | $0.00262 |
| Sonnet 5 | $0.00003 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
choose-order 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 10d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Choose Order
Use this skill when the work is underspecified in method but clear in goal, and the main question is which single engineering lens should own the baton first.
choose-order vs run-cycle: choose-order picks the narrowest first lens for the immediate constraint. run-cycle picks a fuller sequence when the task needs multiple lenses. On the same task, they may give different answers — choose-order says "start here," run-cycle says "walk this path." That divergence is intentional, not a bug.
Inputs required
- task statement
- whether the work is new design, bug triage, refactor, enforcement, rollout, integration, or reliability work
- constraints if already known
Procedure
- Classify the task as new design, bug triage, refactor, risky rollout, enforcement, reliability, integration, naming, observability, accessibility, or scaffolding.
- Pick the narrowest order that names the real constraint:
- Elsecaller for architecture and irreversible choices
- Willshaper for repo shape and scaffolding
- Stoneward for reliability, load, and performance core
- Bondsmith for integration and multi-system choreography
- Lightweaver for naming, docs, and truthful surfaces
- Truthwatcher for evidence, instrumentation, and debugging
- Edgedancer for edge cases, recovery, and accessibility
- Dustbringer for deletion and simplification
- Skybreaker for machine-enforced rules
- Windrunner for blast radius, rollout, and rollback
- If the task is small, choose the minimum viable cycle from
CYCLE.mdinstead of forcing all ten. - Load only the chosen order skill and keep prior hand-off artifacts in context.
Output shape
Return a routing packet with:
- recommended order
- why this order fits best
- artifact to produce
- likely next order if the work continues
- source docs to consult
- minimum viable alternative if the full order feels too heavy
Example invocation
"Use choose-order for: 'we need to split our reporting worker into separate batch and realtime paths without wrecking ops.'"
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.
- 10d ago First seen · 59 lines · 17 tokens per session scan A 9794ed832a58
choose-order is a skill published in the GitHub repository Hmbown/knightsradiant (2 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 525 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.
Other skills, from other repositories
idea-superpowers-suite
Use when running the full idea workflow: capture a rough idea, expand it into design/UI/implementation docs, research similar products, and generate build-ready Markdown artifacts.
idea-to-implementation-doc
Use when reviewing one specific idea/design doc, researching similar products, and producing a separate technical implementation plan or roadmap.
idea-to-design-doc
Use when turning a rough idea into a focused product/design Markdown doc through guided questions, without moving into implementation too early.
idea-to-ui-design-brief
Use when turning a product/design doc into a focused UI design brief, optional AI image-generation concept prompts, and implementation-ready UI direction without replacing the main idea workflow.
engine-bootstrap
Use when no contextualizer exists yet for a set of source URLs or local paths and one needs to be scaffolded from scratch.
refresh
Use when an existing contextualizer's references may have drifted from current upstream state — typically weekly, or whenever a few days of upstream changes have accumulated — to bring them back into agreement.