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/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/memory-report)<a href="https://agentmods.dev/commands/jingxuanc/causal-memory/memory-report"><img src="https://agentmods.dev/badge/commands/jingxuanc/causal-memory/memory-report/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/jingxuanc/causal-memory/memory-report"><img src="https://agentmods.dev/badge/commands/jingxuanc/causal-memory/memory-report.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 | $0.00017 | $0.00281 |
| Opus 5.5 | $0.00007 | $0.00112 |
| Sonnet 5.5 | $0.00003 | $0.00056 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
memory-report 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 1mo 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
Report the health of this workspace's causal memory. Do exactly this:
- Call
prediction_reportand show the verdict — accuracy per method and per task_tag, pending predictions. If the ledger is empty, say so and explain (one sentence) thatcounterfactual_queryverdicts become falsifiable predictions that auto-resolve when either option is later recorded. - Call
causal_directory(limit 10) and summarize what experience exists as a compact bullet list (task_tag — the one-line lesson). - Flag anything notable: task_tags with dense same-context branches
(forks make counterfactuals same-world), falsified predictions
(accuracy < 50% in a stratum means those lessons deserve
invalidate_decision), or stale pending predictions.
Keep the whole report under 200 words. No preamble — start with the prediction ledger line.
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.
- 1mo ago First seen · 23 lines · 17 tokens per session scan A 79d6b3a5cdfc
memory-report is a command published in the GitHub repository JingxuanC/causal-memory (99 stars, last pushed 4d ago), licensed Apache-2.0. It adds 17 tokens to every session and 281 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 2026-09-03.
Other commands, from other repositories
revise-agents-md
Update AGENTS.md with learnings from this session.
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.
modernize-uplift
Same-stack version uplift (e.g. .NET Framework 4.8 → .NET 8) — preserve the code, fix the version deltas, prove equivalence by running one test suite on both runtimes.
modernize-reimagine
Multi-agent greenfield rebuild — extract specs from legacy, design AI-native, scaffold & validate with HITL.
modernize-preflight
Environment readiness check — analysis tools, build toolchain, source completeness, telemetry access.
feature-dev
Guided feature development with codebase understanding and architecture focus.