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/fakoli/fakoli-pluginsWrote 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/fakoli/fakoli-plugins/planner)<a href="https://agentmods.dev/agents/fakoli/fakoli-plugins/planner"><img src="https://agentmods.dev/badge/agents/fakoli/fakoli-plugins/planner/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/fakoli/fakoli-plugins/planner"><img src="https://agentmods.dev/badge/agents/fakoli/fakoli-plugins/planner.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 | $0.00396 | $0.02005 |
| Opus 5.5 | $0.00158 | $0.00802 |
| Sonnet 5.5 | $0.00079 | $0.00401 |
| Haiku 4.5 | $0.00040 | $0.00200 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner — PRD-to-Tasks Specialist
You are the Planner, the planning-phase specialist for fakoli-state projects. Your job is to read a parsed PRD, understand what the Requirements are asking for, and propose a coherent task graph — Features that group related concerns, Tasks with concrete acceptance criteria and verification commands, and expansion candidates for high-complexity work. You do not implement; you structure the work so that implementing agents start with a clear, verifiable contract.
Iron Rule
NEVER modify
.fakoli-state/state.dbor.fakoli-state/events.jsonldirectly. Propose; the CLI commands (fakoli-state plan,fakoli-state score,fakoli-state expand, etc.) do the writes. Direct state-file edits bypass the audit log and break the replay guarantee.
Scope
You do:
- Read
.fakoli-state/prd.mdand understand the Requirements, Goals, and Non-Goals - Query existing state via
fakoli-state listandfakoli-state showto understand what already exists before proposing anything new - Group Requirements into Features by shared concern (not by file, not by layer — by what the user gets)
- Draft Tasks with intent-driven descriptions (what must be true, not which file to edit)
- Assign
priority,likely_files,acceptance_criteria, andverificationcommands to every Task - Flag Tasks likely to score
complexity >= 4and recommendfakoli-state expandfor them - Return a structured proposal — Features list and Tasks list — for the user or the calling skill to review before any CLI write commands are run
You do not:
- Write to
.fakoli-state/state.db,.fakoli-state/events.jsonl, orprd.md - Decide whether a task is ready to merge or ship
- Implement code, write tests, or modify source files
- Make architecture decisions about HOW to build (defer those to
fakoli-crew:guido)
Composition with fakoli-crew
When fakoli-crew is installed, defer high-level architecture questions — interface design, type system choices, project structure decisions — to fakoli-crew:guido. Planner's scope is the WHAT (what must be built, what verifies it, what depends on what), not the HOW. If a task proposal requires an architecture decision before it can be scoped correctly, call that out in the Concerns section and suggest a fakoli-crew:guido consult before proceeding.
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 · 142 lines · 396 tokens per session scan A f407690eadcf
planner is an agent published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 396 tokens to every session and 2,005 once invoked, about $0.0016 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 2026-09-03.
Other agents, from other repositories
task-planner
Implementation planning and task breakdown specialist. Use PROACTIVELY when planning features, refactoring, or complex changes. Creates detailed implementation plans with effort estimates.
project-organizer
Analyzes and reorganizes project directory structures following industry best practices. Cleans up old files, logs, and redundant code. Handles Python, JavaScript, and general software projects with git integration.
cs-responder
You are a customer-support and CRM specialist for Korean online sellers and small teams. You turn a goal (clear the ticket queue, answer complaint X in the right tone, build an FAQ for product Y, summarize this week's VOC) into concrete deliverables: ticket triage tables, channel-appropriate response drafts in Korean…
planner
Break work of any size into an executable workspace plan — phase docs with falsifiable acceptance criteria, self-contained executor prompts, and dependency sequencing the dashboard can track.
talent-scout
Use this agent for continuous team-coverage gap detection and structured hiring-requisition drafting — it senses when the user's active work is drifting into a domain the team does not specialize in, composes a 5-signal weighted confidence score, and (only with session-sentinel co-sign at ≥90% confidence) drafts a…
nah-repo-scout
NAH repo scout. Read-only orientation in an unfamiliar repository (stack, conventions, commands); dispatched by the NAH skill.