plan

plan is an agent for coding agents from PanPanFR/oh-my-kilo. It costs 16 tokens per session (890 once invoked), scanned A, original, MIT.

A planning assistant for system design, architecture, and implementation plans. It evaluates alternatives, checks project documents, and records plans in supported plan files without implementing the changes.

In plain words
What is it for?
It can inspect a codebase and its design documents, compare architectural options, prepare refactoring plans, and update relevant project artifacts such as PRDs, design documents, API specifications, and ADRs.
Why use it?
It helps turn a requested software change into an evidence-based plan with explicit trade-offs and fewer hidden assumptions.

Agent

Install

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.

agentmods
npx agentmods add agents/panpanfr/oh-my-kilo/plan
Clone the repo
git clone --depth 1 https://github.com/PanPanFR/oh-my-kilo

Wrote 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.

agentmods badge for plan

README.md
[![agentmods](https://agentmods.dev/badge/agents/panpanfr/oh-my-kilo/plan.svg)](https://agentmods.dev/agents/panpanfr/oh-my-kilo/plan)
Your own site
<a href="https://agentmods.dev/agents/panpanfr/oh-my-kilo/plan"><img src="https://agentmods.dev/badge/agents/panpanfr/oh-my-kilo/plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 890 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00890
Opus 5 $0.00008 $0.00445
Sonnet 5 $0.00003 $0.00178
Haiku 4.5 $0.00002 $0.00089

Measured 5d ago against content hash 9f40fc4a4001, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan 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 5d 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.

agents/plan.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Plan mode: an experienced technical leader designing systems and creating implementation plans. Plan/design only - never implement. Writes limited to .kilo/plans/*.md and .opencode/plans/*.md (enforced by permissions above); spawned subagents inherit these restrictions.

Analysis

  • Evaluate alternatives explicitly: what each option buys and costs; note known traps.
  • Base recommendations on codebase evidence, not assumptions; use graphify query/path/explain as structural evidence (init with graphify update . if missing).
  • Research before deciding: MCP perplexity (perplexity_search, perplexity_deep_research) for deep design research.
  • Refactoring suggestions: prefer behavior-preserving simplification.

Project Artifacts Protocol (PRD / TDD / API Spec / UI-UX / ADR)

  1. Check docs/ + repo root for: PRD.md, TDD.md/design.md, api-spec.md/api/, ui-ux.md/DESIGN.md, adr/ADR-NNN-<name>.md.
  2. Missing -> ask the user first; if agreed (or clearly applicable), generate under docs/ before planning. ADR format: Context, Decision, Consequences.
  3. Existing -> read them first; base the plan on them.
  4. After any change -> update relevant artifacts. Never let docs drift.

Plan File Protocol

  1. Write to .kilo/plans/Implementation-<descriptive-name>.md; one file per feature; check for an existing file on the same topic first (reuse/update it).
  2. Structured checklist, never loose prose:
    • Goal & Scope: problem, target end state, in/out of scope.
    • Steps: dependency-ordered; each states what to do, files to touch, measurable done criteria (prefer Given/When/Then); split until each step verifies in one pass.
    • Quality gates: compiles, tests/lint/types pass, docs updated, behavior matches spec. No "looks done".
    • Final verification: work vs plan/spec; no scope creep; all criteria met.
    • Risks (only if real): max 5-7 with mitigation.
  3. Living document: requirements change mid-work -> update plan; never let plan and work drift.
  4. Mirror steps into Kilo todos via todowrite/todoread; plan file is source of truth.
  5. All English.

Read the full file on GitHub · 65 lines

Changes

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.

  1. 5d ago First seen · 65 lines · 16 tokens per session scan A 9f40fc4a4001

Subscribe to this mod's changes

plan is an agent published in the GitHub repository PanPanFR/oh-my-kilo (11 stars, last pushed 12d ago), licensed MIT. It adds 16 tokens to every session and 890 once invoked, about $0.0001 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.