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/delightful-ai/beads-rsWrote 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/delightful-ai/beads-rs/agents)<a href="https://agentmods.dev/commands/delightful-ai/beads-rs/agents"><img src="https://agentmods.dev/badge/commands/delightful-ai/beads-rs/agents.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 | $0.00000 | $0.00376 |
| Opus 5 | $0.00000 | $0.00188 |
| Sonnet 5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
AGENTS 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 8d 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
Boundary
This subtree owns per-command CLI behavior, rendering, and request construction.
NEVER: reach into IpcClient, repo discovery, or actor/bootstrap plumbing from a handler just because it needs a typed request.
Routing
- Most handlers follow the IPC path: normalize args, build a typed
Request::*orAdminOp::*, callruntime::sendorsend_raw, then render the typed payload or hand it toprint_ok. - Backend-driven exceptions go through
../backend.rs: copystore.rsfor offline-or-host-backed admin flows, and keepupgrade.rs/migrate.rsin that family instead of forcing them through IPC. setup.rsandonboard.rsare the local file/stdout exception: copy them for editor/config generation flows that do not talk to the daemon.mod.rsis the registry and shared render dispatch. If a new payload needs human output wiring, extend that dispatch instead of open-coding a second switch.common.rsis the first place to extend shared fetch/format helpers before adding another command-local copy.- Copy
list.rsfor query-plus-custom-human rendering,admin.rsfor IPC subcommand fanout into typed ops,create.rswhen a mutation may need fetch-after-create fallback,store.rsfor backend-driven exceptions, andsetup.rsfor local file/config flows. - The global parse/build-runtime split lives across
../cli.rsand../runtime.rs; command handlers should assume setup is already done.
Verification
cargo test -p beads-cli commands::is the quickest proof loop for handler and renderer changes in this subtree.- Run
just dylintif a command change tempts you to reach into daemon internals or host-only seams.
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.
- 8d ago First seen · 17 lines · 0 tokens per session scan A 6b9021172a14
AGENTS is a command published in the GitHub repository delightful-ai/beads-rs (24 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 376 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 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.