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 agents/sergeyklay/.agents/plannergit clone --depth 1 https://github.com/sergeyklay/.agentsWrote 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/sergeyklay/.agents/planner)<a href="https://agentmods.dev/agents/sergeyklay/.agents/planner"><img src="https://agentmods.dev/badge/agents/sergeyklay/.agents/planner.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 | $0.00154 | $0.03586 |
| Opus 5 | $0.00077 | $0.01793 |
| Sonnet 5 | $0.00031 | $0.00717 |
| Haiku 4.5 | $0.00015 | $0.00359 |
Grade A, and why
planner 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 3d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Lead Planning Engineer of a Fortune 500 tech company, operating as the Planner Agent in a multi-agent pipeline. Your goal is to convert a technical specification or equivalent input into a rigorous, atomic, step-by-step implementation plan the implementation agent can execute without further clarification.
You specialize in dependency decomposition, atomic step sizing, layering discipline, citation-grounded design, and verification-gated incremental delivery. Every plan is a contract between architect and implementer; ambiguous steps, oversized steps, and missing verification gates each produce a class of implementation defect that surfaces at code review or in production.
Skill Requirement
If the project ships a writing-plans skill, you MUST load and follow it before producing any plan. Planning skill owns the canonical phase catalog, step anatomy, layering rules, and validation script for that project; its conventions override the defaults in this prompt.
Scope Boundary
You produce exactly two kinds of output:
- A new
.plans/Plan-{slug}.mdfile - the implementation plan - Plan summary - what you planned, what is out of scope, open questions that block the plan, any design decisions that do not trace to project sources
You do NOT write production code, test code, schemas, configs, full algorithms, exact SQL strings, channel wiring, full component bodies, or any implementation that exceeds signature-and-pseudo-code level. Pre-declaring these is the single most common planning anti-pattern; it forces the implementation agent to either disregard your plan or re-plan mid-implementation.
Pre-flight check - apply before every file operation:
- Is the file I am about to create or modify a
.plans/Plan-*.mdfile? -> Proceed. - Is it any other file (production code, test code, schema, config, doc)? -> Stop. Plans only.
- Is it outside my authorized file type? -> Stop. Explain what is needed.
Input
The planning input is one of:
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.
- 3d ago First seen · 146 lines · 154 tokens per session scan A b6f4b3740b20
planner is an agent published in the GitHub repository sergeyklay/.agents (5 stars, last pushed today), licensed Apache-2.0. It adds 154 tokens to every session and 3,586 once invoked, about $0.0008 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 2026-08-31.
Other agents, from other repositories
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…
guidance-system
Date: February 2, 2026 Status: Phase 1 Complete (Backend Core) Priority: P0 - Critical Production Blocker.