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/gastownhall/beads/importgit clone --depth 1 https://github.com/gastownhall/beadsWrote 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/gastownhall/beads/import)<a href="https://agentmods.dev/commands/gastownhall/beads/import"><img src="https://agentmods.dev/badge/commands/gastownhall/beads/import.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 | $0.00007 | $0.00997 |
| Opus 5 | $0.00003 | $0.00498 |
| Sonnet 5 | $0.00001 | $0.00199 |
| Haiku 4.5 | $0.00001 | $0.00100 |
Grade A, and why
import 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bd import imports newline-delimited JSON into an existing Beads database.
Issues with new IDs are created and existing IDs use guarded upsert semantics.
The command is not supported in proxied-server mode.
Usage
bd import # Read .beads/<import.path>
bd import backup.jsonl # Read a specific file
bd import --input backup.jsonl # Same as -i backup.jsonl
bd import - # Read JSONL from stdin
bd export --include-memories | bd import - # Round-trip issues and memories
bd import --dry-run backup.jsonl # Parse and report without writing
bd import --json backup.jsonl # Return a structured result
With no file argument, the source is the import.path file under .beads/;
import.path defaults to issues.jsonl. Use either a positional file or
--input/-i, not both. The special path - reads stdin. With --global and
no file, the source is global-issues.jsonl in the active Beads directory.
Each non-empty line must be a JSON object. Issue records accept the schema
emitted by bd export; title is the only required issue field. Records with
"_type":"memory" and non-empty key and value fields are imported as
persistent memories. Optional export header records are ignored, and tombstone
rows are skipped. bd export omits memories by default; add
--include-memories or --all when they should be carried into an import.
Merge and Safety Semantics
For records that supply updated_at, an incoming row rewrites an existing
issue only when its timestamp is strictly newer. Older records are skipped
wholesale, including their labels, comments, and dependencies. When timestamps
are equal, the local issue row wins, while those auxiliary records still merge.
The stale check is repeated inside the upsert so a concurrent newer local update
is not overwritten.
If updated_at is omitted, the importer fills it with the current time during
the write. A record naming an existing ID can therefore overwrite local state;
include the exported timestamp when stale protection matters.
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.
- 4d ago First seen · 85 lines · 7 tokens per session scan A 604e48e6d093
import is a command published in the GitHub repository gastownhall/beads (26,853 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 997 once invoked, about $0.0000 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
Context Search
Search prior work to add context to a request, or browse previous sessions on a topic. Use before/after a request to ground it in past work, or standalone to recall and familiarize before asking. Shortcut for the Cortex skill's recall workflow.
cs
Search prior work to add context to a request, or browse previous sessions on a topic. Shortcut for the Cortex skill's recall workflow.
lavra-learn
Curate raw knowledge comments into structured, well-tagged entries for future auto-recall.
lavra-recall
Search knowledge base mid-session and inject relevant context.
lavra-checkpoint
Save session progress by filing beads, capturing knowledge, and syncing state.
ingest-pr
Command "ingest-pr" from Avos-Lab/git-aware-coding-agent, covering avos ingest-pr, usage, description, arguments and options.