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/implementgit 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 | $0.00017 | $0.00561 |
| Opus 5 | $0.00009 | $0.00280 |
| Sonnet 5 | $0.00003 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
implement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute the implementation plan in docs/thoughts/$ARGUMENTS step by step and run the quality gate when done.
What to do
Read docs/thoughts/$ARGUMENTS/plan.md in full before doing anything else.
If docs/thoughts/$ARGUMENTS/progress.md exists, read it too — it means a previous session started this task.
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.
Load all skills listed in the plan's "Skills to Update" section before writing any code.
Execute each step from the plan in order. For each step:
- Announce which step you are starting.
- Make the changes specified.
- Run the verification command listed in the step, if any.
- Mark the step complete in
docs/thoughts/$ARGUMENTS/progress.md(see format below). - If verification fails, fix the issue before moving to the next step.
After all steps are complete, run the full quality gate, based on the AGENTS.md.
Fix any failures before declaring the task done.
After the quality gate passes, update any skill files listed in the plan's "Skills to Update" section to reflect the implementation changes.
Maintain docs/thoughts/$ARGUMENTS/progress.md throughout so the task can be resumed if the session is interrupted:
# Progress: <task description>
## Status
In progress / Complete
## Completed Steps
- [x] Step 1: <title>
- [x] Step 2: <title>
## Current Step
- [ ] Step 3: <title>
<any notes on where you left off or issues encountered>
## Remaining Steps
- [ ] Step 4: <title>
- [ ] Step 5: <title>
## Issues
<any blockers or decisions made that deviate from the plan>
Update Status: Complete and remove the "Current Step" block when all steps and the quality gate pass.
Rules you must follow
- Never create git commits.
- Quality gate must pass before the task is declared done.
- Update skills after implementation. Stale skills mislead future sessions.
- Follow the plan step order. Do not skip or reorder steps without noting it in Issues.
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 · 66 lines · 17 tokens per session scan A f3b0a61ee499
implement is a command published in the GitHub repository mazumba/opencode-dockerized (5 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 561 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.