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/jingxuanc/causal-memory/recallgit clone --depth 1 https://github.com/JingxuanC/causal-memoryWrote 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/jingxuanc/causal-memory/recall)<a href="https://agentmods.dev/commands/jingxuanc/causal-memory/recall"><img src="https://agentmods.dev/badge/commands/jingxuanc/causal-memory/recall.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00335 |
| Opus 5 | $0.00006 | $0.00168 |
| Sonnet 5 | $0.00003 | $0.00067 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Before acting on "$ARGUMENTS", recall everything relevant from causal memory:
- Call
search_memorywith "$ARGUMENTS" (fused facts + causal lessons). - If any hit's task_tag looks like the current domain, call
search_causalrestricted to that tag for depth. - Judgment call, two concrete options in play? Call
counterfactual_querywith BOTH option texts — same-context branches (natural experiments) beat pooled statistics when they exist. - Risky or irreversible action? Call
intervention_queryon it and heed the safe/warning/danger label.
Then answer, in this order:
- Relevant experience (max 5 bullets: decision → outcome, with task_tag and confidence)
- What it implies for "$ARGUMENTS" (one short paragraph)
- If you are about to record anything new afterwards, remember to pass
contextonrecord_decision— especially when options were weighed.
If memory holds nothing relevant, say so plainly and proceed; absence of evidence is not evidence of safety.
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 · 29 lines · 13 tokens per session scan A 77ac467a2a29
recall is a command published in the GitHub repository JingxuanC/causal-memory (67 stars, last pushed 3d ago), licensed Apache-2.0. It adds 13 tokens to every session and 335 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 2026-09-03.
Other commands, from other repositories
warden-select
Measure pending token-warden candidate rules for an agent on the golden suite, evict or activate them, and recompile the agent's memory.
review
Run an adversarial review. Raw arguments: $ARGUMENTS.
ship
Prepare a release checklist.
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.