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/stratalab/strata-coreWrote 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/stratalab/strata-core/graph.batch_write)<a href="https://agentmods.dev/commands/stratalab/strata-core/graph.batch_write"><img src="https://agentmods.dev/badge/commands/stratalab/strata-core/graph.batch_write/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/stratalab/strata-core/graph.batch_write"><img src="https://agentmods.dev/badge/commands/stratalab/strata-core/graph.batch_write.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 | $0.00000 | $0.00242 |
| Opus 5.5 | $0.00000 | $0.00097 |
| Sonnet 5.5 | $0.00000 | $0.00048 |
| Haiku 4.5 | $0.00000 | $0.00024 |
Grade A, and why
graph.batch_write 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
Applies a list of graph operations - upsert_node, delete_node, upsert_edge, delete_edge - in one engine commit. Validation failures (bad ids, missing edge endpoints, frozen-ontology violations) reject the whole batch; nothing is partially applied. The response reports one positional item result per operation, all sharing the same commit receipt.
This whole-batch atomicity is deliberate, and differs from the itemwise kv, json, and event batch writes (where the valid items of a mixed batch still commit and the invalid one carries a typed per-item error). A graph batch mixes node and edge upserts, and an edge references its endpoint nodes, so applying only the valid items could leave an edge pointing at a node that never landed. Rejecting the whole batch keeps graph references consistent - referential integrity is the reason the graph channel is atomic where its siblings are itemwise.
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 Changed · +2 lines 14f209f5511d
- 1mo ago First seen · 7 lines · 0 tokens per session scan A cffb15deb56e
graph.batch_write is a command published in the GitHub repository stratalab/strata-core (3 stars, last pushed 17d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 242 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 2026-08-31.
Other commands, from other repositories
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.