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 skills/semantica-agi/semantica/temporalnpx skills add semantica-agi/semantica --skill temporalgit clone --depth 1 https://github.com/semantica-agi/semanticaWhat 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 | $0.00000 | $0.01134 |
| Opus 5 | $0.00000 | $0.00567 |
| Sonnet 5 | $0.00000 | $0.00227 |
| Haiku 4.5 | $0.00000 | $0.00113 |
Grade A, and why
temporal 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/semantica:temporal
Temporal graph operations. Usage: /semantica:temporal <sub-command> [args]
$ARGUMENTS = sub-command + query/node + date expression.
query "<question>" [at|before|after <date>]
Temporally-scoped natural-language graph query.
from semantica.kg.temporal_query_rewriter import TemporalQueryRewriter
from semantica.kg.temporal_normalizer import TemporalNormalizer
normalizer = TemporalNormalizer()
# Normalize natural date expressions: "last month", "Q3 2024", "2025-01-15"
date = normalizer.normalize(date_expr)
rewriter = TemporalQueryRewriter()
# Rewrite query with temporal constraint
rewritten = rewriter.rewrite(
query=question,
temporal_constraint={"op": direction, "value": date}, # op: "at"|"before"|"after"
)
Then run the rewritten query through AgentContext.retrieve() or ContextGraph.query().
Return ranked results with Valid From, Valid Until, Active At <date> columns. Mark nodes that were not yet created at the target time as [not yet created].
snapshot <date>
Reconstruct the full graph state as it existed at a specific point in time.
from semantica.context import ContextGraph
graph = ContextGraph(advanced_analytics=True)
# state_at returns a dict snapshot of the graph at that timestamp
snapshot = graph.state_at(timestamp=date) # ISO string or datetime
Output:
Graph snapshot at <date>:
Nodes: N (M added since prev snapshot, K removed)
Edges: P
Density: 0.21
Communities: Q
Active decision categories at <date>:
| Category | Count | Avg Confidence |
Top 10 nodes (by degree at <date>):
| Node | Type | Degree |
[Compact Mermaid graph TD — top-10 most connected nodes at that time]
timeline <node_id>
Show attribute and relationship changes for a node across its full history.
from semantica.context import ContextGraph
graph = ContextGraph()
# Use state_at() at multiple time points to reconstruct history
# Check add_node timestamps and edge addition times from graph data
node_data = graph.find_node(node_id)
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 · 165 lines · 0 tokens per session scan A b5f65e9a0de8
temporal is a skill published in the GitHub repository semantica-agi/semantica (11,359 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,134 tokens. 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 skills, from other repositories
ai-instruction-detox
AI 指令排毒與規則治理：把散落在 CLAUDE.md、AGENTS.md、skills、context、memory 的規則 原子化、查衝突、去重複、找過時、揪 Prompt Injection，產出可套用的精簡架構與回復方案。 觸發時機：用戶說「指令排毒」「規則太亂」「CLAUDE.md 太長」「規則互相矛盾」「上下文減肥」 「AI 設定治理」「多個 Agent 規則分裂」「context 膨脹」，或要求審查／清理 AI 指令檔。 不要觸發：一般程式重構、產品程式碼審查、單純想縮短一份文件（那是編輯不是治理）。.
compile
Compile a deterministic CIGAR context bundle for the current task with an explicit token budget and inspectable manifest.
effect
Prepare, inspect, commit, and reconcile governed CIGAR effects while preserving explicit authorization and idempotency.
why
Explain the provenance, authority, expiry, degradation state, and token accounting of CIGAR context already presented in this session.
checkpoint
Create an inspectable CIGAR checkpoint before compaction, interruption, or a meaningful task boundary.
handoff
Create or accept a recipient-specific CIGAR handoff without forwarding the parent conversation transcript.