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/jumppad-labs/spektacularWrote 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/jumppad-labs/spektacular/spek-knowledge)<a href="https://agentmods.dev/commands/jumppad-labs/spektacular/spek-knowledge"><img src="https://agentmods.dev/badge/commands/jumppad-labs/spektacular/spek-knowledge/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/jumppad-labs/spektacular/spek-knowledge"><img src="https://agentmods.dev/badge/commands/jumppad-labs/spektacular/spek-knowledge.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 | $0.00015 | $0.00029 |
| Opus 5.5 | $0.00006 | $0.00012 |
| Sonnet 5.5 | $0.00003 | $0.00006 |
| Haiku 4.5 | $0.00002 | $0.00003 |
Grade A, and why
spek-knowledge 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 2mo 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
Run the spek-knowledge skill.
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.
- 2mo ago First seen · 6 lines · 15 tokens per session scan A 1332bd0cc055
spek-knowledge is a command published in the GitHub repository jumppad-labs/spektacular (20 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 29 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 2026-08-30.
Other commands, from other repositories
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.
kiro-steering
Command "kiro-steering" from gotalab/cc-sdd, covering kiro steering management, scenario detection, bootstrap flow, sync flow and granularity principle.
steering
Manage {{KIRODIR}}/steering/ as persistent project knowledge.
context-hygiene
Audit the knowledge store for contradictions and stale entries; raise at most 3 contradictions per run as Decision Catalog items and report stale entries as questions. Monthly cadence.
context-capture
Capture facts from a conversation, document or finding as inferred knowledge entries with a confidence band and a re-verify note; a correction supersedes the earlier entry.
autospec.implement
Execute the implementation plan by processing tasks defined in tasks.yaml.