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/abilityai/cornelius/recallgit clone --depth 1 https://github.com/Abilityai/corneliusWhat 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 | $0.00018 | $0.00450 |
| Opus 5 | $0.00009 | $0.00225 |
| Sonnet 5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
recall 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- recall — 100% identical, 0 lines differ
What it actually says
Semantic Knowledge Retrieval
You are tasked with retrieving relevant knowledge from the Obsidian vault using multi-layer semantic search.
Search Query
$ARGUMENTS
Instructions
-
First Layer - Initial Search:
- Use
mcp__smart-connections__search_noteswith the query above - Retrieve top 5 most relevant notes (threshold: 0.5)
- Use
Readtool to read the full content of the top 2 results
- Use
-
Second Layer - Direct Associations:
- For the top result from layer 1, use
mcp__smart-connections__get_similar_notes - Retrieve 5 semantically similar notes (threshold: 0.6)
- Use
Readtool to read the full content of the top 2 similar notes
- For the top result from layer 1, use
-
Third Layer - Extended Network:
- Build a connection graph using
mcp__smart-connections__get_connection_graph - Parameters: depth=3, max_per_level=5, threshold=0.65
- This reveals deeper conceptual connections
- Build a connection graph using
Output Format
Present the findings in this structured format:
# Knowledge Recall: [Query Topic]
## Layer 1: Direct Matches
[List notes found with similarity scores and key excerpts]
## Layer 2: First-Degree Associations
[List similar notes with their connections and excerpts]
## Layer 3: Extended Network
[Show the connection graph with relationship strengths]
## Key Insights
[Synthesize the main themes and connections discovered]
## Relevant Content
[Include the most pertinent excerpts from the retrieved notes]
Important Notes
- Focus on quality over quantity
- Highlight unexpected connections
- Provide enough context for the user to understand the relevance
- If search returns no results, try broader terms or related concepts
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 · 59 lines · 18 tokens per session scan A f9cfdd08ef2b
recall is a command published in the GitHub repository Abilityai/cornelius (104 stars, last pushed 9d ago), licensed MIT. It adds 18 tokens to every session and 450 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 2026-08-30.
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.