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/cofin/flow/flow-researchgit clone --depth 1 https://github.com/cofin/flowWhat 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 | $0.00009 | $0.00455 |
| Opus 5 | $0.00005 | $0.00228 |
| Sonnet 5 | $0.00002 | $0.00091 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
flow-research 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.
What it actually says
{
"agent": null,
"argument_schema": {
"optional": [],
"required": [
"topic"
],
"syntax": "<topic>"
},
"bounds_enforcement": "agent_validated",
"canonical_id": "flow/research",
"capability_evidence": "Claude Code declared AskUserQuestion contract",
"choice_max": 4,
"choice_min": 2,
"completion_gates": [
"evidence_captured"
],
"custom_answer_behavior": "native_custom_input",
"disabled_choice_policy": "omit",
"fallback": "Use Flow to research this topic",
"git_tags": "forbidden",
"host": "claude_code",
"instruction": "Load the lifecycle owner and follow the canonical procedure source directly.",
"interaction_mode": "structured_choice",
"invocation": "/flow-research",
"kind": "flow_command_adapter",
"lifecycle_owner": "flow-planning",
"multi_select": true,
"mutability": "planning_write",
"mutual_exclusion": true,
"plan_capability": "preferred",
"procedure_source": "skills/flow/references/research.md",
"question_capability": "structured-choice-v1",
"question_permission_check": "declared_and_allowed",
"question_tool": "AskUserQuestion",
"question_transport": "conditional_native",
"runtime_dependency": "agent_file_tools_only",
"sequential_fallback": true,
"shared_contracts": [
"flow-state-v1",
"structured-choice-v1"
],
"state_operations": [
"note",
"discover"
],
"supported_selection_modes": [
"binary",
"single_select",
"multi_select"
]
}
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 · 61 lines · 9 tokens per session scan A 1a1669b245c9
flow-research is a command published in the GitHub repository cofin/flow (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 9 tokens to every session and 455 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
handoff
Hand off a bead to an AI agent for implementation.
context-new
Create a new GitHub repository with AllBeads pre-configured.
Agent Mail for real-time coordination between agents.
project-new
Plan a new project - create repo and beads, but don't code yet.
create
Create a bead in a specific context (cross-repo task handoff).
workflow
Show the AllBeads workflow guide.