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 agentmods add skills/artttj/rapid-stack/specnpx skills add artttj/rapid-stack --skill specgit clone --depth 1 https://github.com/artttj/rapid-stackWhat 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 | $0.00035 | $0.00394 |
| Opus 5 | $0.00017 | $0.00197 |
| Sonnet 5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
spec 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 yesterday.
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
op:spec
Turn a feature ask into an approved spec. Write for your future executor: behavior and tests, not prose.
Steps
- Effort check: for a non-trivial feature, suggest raising to xhigh/max (arrow-choice), continue on answer.
- Clarify with at most 3 arrow-choice questions (purpose, constraints, success criteria). Skip what the ask already answers. For a genuinely unshaped problem use superpowers:brainstorming first; otherwise stay lean.
- Derive
<slug>: kebab-case, 2–4 words, from the feature title. - Write
docs/specs/<slug>/spec.mdin the target repo:
---
status: draft
---
# <title>
## Goal
One paragraph: what exists after this ships, and why.
## Behavior
One bullet per observable behavior. Edge cases included.
## Architecture
Files to touch, data flow, integration points. Quote one real repo convention (file:line) this will follow.
## Tests
The named tests that prove Behavior.
## Out of scope
What this deliberately does not do.
## Open questions
Empty when approved.
- Present the spec, then the gate (arrow-choice): approve / edit / discard.
- approve → set
status: approved, addapproved: <YYYY-MM-DD>, commit (docs: add <slug> spec), offer /op:plan as the next arrow-choice. - edit → apply, re-present.
- approve → set
- Hard stop: no plan and no code for this feature until
status: approvedand Open questions is empty.
Proof at end: the spec path and its frontmatter status.
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.
- yesterday First seen · 48 lines · 35 tokens per session scan A ca411242b5da
spec is a skill published in the GitHub repository artttj/rapid-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 394 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 2026-08-31.
Other skills, from other repositories
autopilot
Full autonomous execution from idea to working code.
plannotator-annotate
Open Plannotator's annotation UI for a file, folder, or URL, then address the returned annotations.
statistical-power
Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers…
chase-travel
Search Chase UR travel portal via Patchright for cash prices, points pricing, Points Boost offers, and Chase Edit hotel benefits. Use for pay-with-points portal comparison on Sapphire Reserve/Preferred.
points-valuations
Cents-per-point (cpp) valuations across major loyalty programs from four publications. Floor/ceiling rules for deciding if a redemption is good or exceptional.
awardwallet
Query AwardWallet for loyalty program balances, elite status, and transaction history. Use when checking points inventory, airline status, or planning trips on points.