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/chriswritescode-dev/opencode-forgeWrote 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/commands/chriswritescode-dev/opencode-forge/review-plan)<a href="https://agentmods.dev/commands/chriswritescode-dev/opencode-forge/review-plan"><img src="https://agentmods.dev/badge/commands/chriswritescode-dev/opencode-forge/review-plan/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/commands/chriswritescode-dev/opencode-forge/review-plan"><img src="https://agentmods.dev/badge/commands/chriswritescode-dev/opencode-forge/review-plan.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 | $0.00000 | $0.00541 |
| Opus 5.5 | $0.00000 | $0.00216 |
| Sonnet 5.5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
review-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 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are reviewing a completed implementation against its original plan.
Input: $ARGUMENTS
Step 1: Find the Plan and Implementation
Use the input to determine what to review:
- If the user provided a loop name, call
plan-readwithloop_namefor that loop. - If the user provided plan text, treat it as the plan and inspect the current working tree implementation.
- Otherwise, call
plan-readwith no arguments to load the current session plan.
If no plan is found using the above rules:
- Call
plan-readwithrecent: trueto list recent project plans. - If the user's words include a feature name, branch clue, or domain term, call
plan-readwithrecent: trueandpatternusing that term. - If multiple plausible plans exist, ask the user to choose.
Do not use loop management tools.
Step 2: Gather Implementation Evidence
Review the implementation that corresponds to the plan:
- Inspect diffs, changed files, and relevant tests for the selected loop or current working tree.
- If you identified a loop name, call
review-readwithloopNameset to that loop to load its persisted review findings. Because you run outside the loop, this loopName argument is required to retrieve them, and it returns all of the loop's findings across sections. - Read the full files needed to verify behavior, not just diffs.
- Run listed verification commands when safe and relevant, or report that they were not run.
- Check existing patterns before claiming a mismatch.
Step 3: Review Criteria
Focus on plan compliance and implementation quality:
- Every acceptance criterion is satisfied by code, tests, or documented behavior
- Required tests and validation commands exist and pass
- The implementation matches the plan's intended scope without unrelated changes
- Deviations from the plan are documented and technically justified
- Edge cases, migrations, compatibility, and rollback concerns from the plan are handled
- The implementation follows existing architecture, naming, and domain patterns
- No duplicated abstractions, dead code, or unnecessary complexity was introduced
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 · 57 lines · 0 tokens per session scan A 514a8d6ece6b
review-plan is a command published in the GitHub repository chriswritescode-dev/opencode-forge (13 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 541 tokens. 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.
Other commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
refactor
Systematic code refactoring with smart scope detection.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).