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 commands/elbalen/skopus/querygit clone --depth 1 https://github.com/elbalen/skopusWhat 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 | $0.00007 | $0.00340 |
| Opus 5 | $0.00003 | $0.00170 |
| Sonnet 5 | $0.00001 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
query 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 2d 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
/query
Answer a question by synthesizing from the vault. $ARGUMENTS is the question.
Steps
-
Read
wiki/index.mdto understand what's available. -
Identify relevant pages by matching on titles, summaries, and implied tags.
-
Read those pages. Follow
[[wikilinks]]one level deep if needed for the question. Don't go deeper unless explicitly required. -
Synthesize a comprehensive answer:
- Lead with a direct answer
- Cite wiki pages inline using
[[wikilinks]] - Show how pages connect when the answer spans multiple
- Mention raw sources when cited in pages
-
If the answer reveals a gap (sub-question the wiki can't fully answer), note it:
💡 Gap noticed: no page exists for X. Consider
/ingestor/compileto add it. -
If the answer is substantial and reusable (3+ paragraphs of synthesis), offer to save it:
This answer is reusable. Save as a new wiki page in
wiki/concepts/or tooutput/? -
Do NOT modify any wiki files.
/queryis read-only. User must explicitly accept the save offer.
Rules
- Cite everything.
- Be honest about gaps — don't fabricate.
- One level deep on wikilink following.
- Prefer wiki over web search — trust curated knowledge first.
- If the answer contradicts a wiki page, flag it and recommend
/lint.
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.
- 2d ago First seen · 38 lines · 7 tokens per session scan A b0c8704820f4
query is a command published in the GitHub repository elbalen/skopus (4 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 340 once invoked, about $0.0000 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 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.