update-plan

A command for updating an existing implementation plan after new questions have been answered. The plan is a written record of the work, its checks, and its rollback steps.

In plain words
What is it for?
Use it to revise a plan’s open questions, file paths, step order, verification commands, and rollback details.
Why use it?
It keeps an existing plan accurate without changing the code or creating a new plan from scratch.

Command

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 commands/mazumba/opencode-dockerized/update-plan
Clone the repo
git clone --depth 1 https://github.com/mazumba/opencode-dockerized
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 343 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 $0.00012 $0.00343
Opus 5 $0.00006 $0.00171
Sonnet 5 $0.00002 $0.00069
Haiku 4.5 $0.00001 $0.00034

Measured yesterday against content hash 872ae3d4538b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-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 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.

.opencode/config/commands/update-plan.md · 45 lines

What it actually says

Update the existing implementation plan in docs/thoughts/$1 using this new information: $2.

What to do

Read docs/thoughts/$1/plan.md in full before doing anything else. Update and overwrite docs/thoughts/$1/plan.md only.

If explore is unavailable in this execution context (for example, inside a subtask agent), use direct tools (glob/grep/read) for codebase discovery and reading without asking for fallback confirmation.

Apply the new information from $2 to:

  • resolve previously open questions or ambiguities
  • adjust step order, files, and verify commands as needed
  • keep the plan concrete and implementation-ready

Preserve the existing plan structure:

  • Overview
  • Prerequisites
  • Implementation Steps
  • Quality Gate
  • Skills to Update
  • Rollback

Rules you must follow

  • Plan-only change. Do not implement code.
  • Update only plan.md in the specified artifact folder.
  • No git commits.
  • Keep exact file paths in each step.
  • Every step must include a Verify command.

Completion Contract (strict)

End the research task with exactly these lines and nothing else, replacing the placeholders: This sentence is the handoff artifact for RPI phase 2. The main agent must relay this information to the user and nothing else:

  • _
  • Open Questions: <list any open questions or "None">
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. yesterday First seen · 45 lines · 12 tokens per session scan A 872ae3d4538b

Subscribe to this mod's changes

update-plan is a command published in the GitHub repository mazumba/opencode-dockerized (5 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 343 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 2026-08-31.