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/cofin/flowWrote 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/agents/cofin/flow/plan-generator)<a href="https://agentmods.dev/agents/cofin/flow/plan-generator"><img src="https://agentmods.dev/badge/agents/cofin/flow/plan-generator/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/agents/cofin/flow/plan-generator"><img src="https://agentmods.dev/badge/agents/cofin/flow/plan-generator.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 | $0.00018 | $0.00346 |
| Opus 5.5 | $0.00007 | $0.00138 |
| Sonnet 5.5 | $0.00004 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
plan-generator 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
{
"canonical_id": "plan-generator",
"canonical_source": "agents/plan-generator.md",
"git_tags": "forbidden",
"host": "vscode_copilot",
"instruction": "Read and follow the canonical agent source directly.",
"interaction_requirement": "structured_choice_optional",
"invariant_ids": [
"flow-state-v1",
"structured-choice-v1",
"planning-convergence-v1",
"git-no-tags-v1"
],
"kind": "flow_agent_adapter",
"question_capability": {
"bounds_enforcement": "unsupported",
"choice_max": null,
"choice_min": null,
"custom_answer_behavior": "sequential_text_only",
"disabled_choice_policy": "omit",
"evidence": "No verified Flow-native VS Code Copilot question tool",
"multi_select": false,
"mutual_exclusion": false,
"permission_check": "not_applicable",
"sequential_fallback": true,
"supported_modes": [],
"tool": null,
"transport": "sequential_text"
},
"tool_capability_requirements": [
"file_read",
"file_write",
"sequential_choice"
]
}
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 First seen · 45 lines · 18 tokens per session scan A 13c38d01a7ab
plan-generator is an agent published in the GitHub repository cofin/flow (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 346 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
beads-warden
Guard the beads execution record: enforce the write-flush-verify discipline that defeats the bd rapid-write race, audit epic dependency graphs for cycles and orphans, catch closures whose title overstates what shipped, flag open beads carrying no disposition or a disproven premise, and reconcile bd against its GitHub…
yegge
Primary session agent for this project. Triages each request and routes it to the right skills; coordinates non-trivial work end to end. All user requests come through it.
beads-guru
Use this agent for general beads (bd) expertise — the three-layer mirror (bd to GitHub to Plane via bd-sync), plain-English bead naming, the JSONL throttle and export model, the source-of-truth hierarchy, and bead hygiene audits. It is the generalist that explains bd discipline and points to the specialist agents for…
evaluator
Independent, read-only acceptance grader. Invoked at the end of a task to verify it is REALLY done. Default-FAIL — every criterion starts false and only flips to PASS with direct evidence. Catches silent downscoping, disabled tests, and over-graded work. Cannot write code.
qa-engineer
Use this agent for manual and exploratory testing of web applications through the browser. Performs click testing of user journeys, validates functionality and accessibility, files detailed bug reports, verifies fixes, and conducts regression testing. Uses Playwright and Chrome DevTools MCP servers for browser…
agile-delivery-lead
Agile delivery leadership for project management, sprint planning, backlog refinement, risk tracking, and stakeholder communication. Use for planning, forecasting, and process improvement.