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 commands/mazumba/opencode-dockerized/plangit clone --depth 1 https://github.com/mazumba/opencode-dockerizedWhat 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 | $0.00015 | $0.00614 |
| Opus 5 | $0.00008 | $0.00307 |
| Sonnet 5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00061 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn the research document in docs/thoughts/$1 into a concrete, step-by-step implementation plan.
What to do
Read docs/thoughts/$1/research.md in full before doing anything else.
Write your output to docs/thoughts/$1/plan.md.
If the research document contains Open Questions that are not yet answered, state that planning cannot proceed and list what needs to be resolved first.
Check, if these are the answers to the Open Questions and resolve them in the plan file, if that is the case: $2.
Also read AGENTS.md to ensure the plan respects all project constraints and verification expectations. Load relevant skills from .opencode/skills/ for any domain touched by the task.
Use direct tools (glob/grep/read) for codebase discovery and reading without asking for fallback confirmation.
Write plan.md using this structure (target ~150–200 lines):
# Plan: <task description>
## Overview
<goal, approach, and any architectural decisions>
## Prerequisites
<anything that must be true or done before starting — env, migrations, deps>
## Implementation Steps
### Step 1: <short title>
**Files:** `path/to/file`, `path/to/other`
**Changes:** <precise description of what to add/change/remove>
**Verify:** <command or assertion to confirm this step is correct before moving on>
### Step 2: ...
(continue for all steps)
## Quality Gate
After all steps: Run quality gates as provided by the AGENTS.md
## Skills to Update
<list any `.opencode/skills/` files that must be updated after implementation to reflect the changes>
## Rollback
<how to undo the changes if something goes wrong>
Rules you must follow
- No code changes. Your only output is the plan document.
- Unresolved Open Questions block planning. List them and stop — do not guess.
- Read AGENTS.md before writing any steps.
- Load relevant skills for every domain the plan touches.
- Reference exact file paths in every step — not directories.
- Every step needs a Verify command so progress is checkable.
- Flag schema and asset steps — any step touching DB schema needs a migration; any step touching assets needs initialization.
- Never create git commits.
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.
- yesterday First seen · 71 lines · 15 tokens per session scan A 27f07f01230a
plan is a command published in the GitHub repository mazumba/opencode-dockerized (5 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 614 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.