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/compilegit 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 | $0.00009 | $0.00410 |
| Opus 5 | $0.00005 | $0.00205 |
| Sonnet 5 | $0.00002 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
compile 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
/compile
Capture valuable knowledge from the current session into the vault before it evaporates into chat history. The most important wiki command — it's what makes the wiki compound across sessions.
$ARGUMENTS is an optional topic focus.
Steps
-
Review the conversation for:
- Architectural decisions (with rationale and tradeoffs)
- Patterns discovered
- Gotchas encountered
- Problems solved (fix + root cause)
- Tools evaluated (chosen, rejected, why)
- Configurations that worked
- Non-obvious empirical facts (latencies, limits, version quirks)
-
Filter noise. Skip trivial fixes and anything already in git history. Bar: would future-me want to find this in 3 months?
-
If
$ARGUMENTSis provided, scope extraction to that topic. -
For each piece of knowledge: check
wiki/index.mdfor existing pages. Update existing (preferred) or create new. If contradicted, add> ⚠️ Contradiction:callout. -
Cross-link with
[[wikilinks]]. -
Update
wiki/index.md. -
Append to
log.md:## [YYYY-MM-DD HH:MM] compile | <Topic or "Session knowledge"> <Brief description.> Pages touched: [[page-1]], [[page-2]] -
Git commit:
compile: <topic or 'session knowledge'>. -
Print a summary of what was captured.
Rules
- Be honest about what's new vs. already-known.
- Don't inflate — if a session produced nothing wiki-worthy, say so and skip the commit.
- Capture the why, not just the what.
- Capture surprises — the most valuable entries are things that contradicted assumptions.
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 · 49 lines · 9 tokens per session scan A 7056f2b784b3
compile is a command published in the GitHub repository elbalen/skopus (4 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 410 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
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.