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/fmflurry/settings-opencode/cop-reviewgit clone --depth 1 https://github.com/fmflurry/settings-opencodeWhat 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 | $0.00000 | $0.00603 |
| Opus 5 | $0.00000 | $0.00302 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
cop-review 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cop-review — Pre-Merge Review
Review the current branch against a target branch before merging.
Stack-aware delegation
Detect the project stack in cwd from these signals, then delegate via Agent tool to the matching subagent:
| Signal | Stack | Subagent to delegate to | Tooling |
|---|---|---|---|
angular.json present |
Angular + TypeScript | angular-cop |
npx tsc --noEmit + npm run lint |
*.csproj / *.sln / *.slnx / global.json present |
.NET | dotnet-cop |
dotnet build --nologo -clp:ErrorsOnly + dotnet format --verify-no-changes |
If BOTH are present (rare monorepo), check which language the diff files are in (.ts/.html → angular-cop; .cs/.csproj → dotnet-cop). Delegate to both subagents when the diff contains both language groups. If ambiguous, default to angular-cop and note the ambiguity in your findings.
Usage
/cop-review <target-branch> [--level=junior|senior] [--scope=...] [--no-tools]
<target-branch>(required) — the branch the PR will merge into (e.g.main,develop,release/2026.05).--level=junior— verbose teaching mode with rationale + doc links for every finding.--level=senior(default) — terse one-liners.--scope=...— limit to a subset of checklists. Comma list. Defaults to all.--no-tools— skip tooling checks and produce static review only (faster).
What you do
- Parse the arguments:
- Extract the target branch from the first positional argument.
- If target is missing, print usage and stop.
- Detect the stack from the signals above.
- Call
Agentwithsubagent_type: "angular-cop"orsubagent_type: "dotnet-cop"(or both for monorepos with mixed content), passing the full command arguments. The subagent owns the rest: resolve the review window, load the applicable skill(s), run tooling, and render the report. - Synthesis: Subagents report findings only. After they complete, synthesize and return the unified review to the user.
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 · 45 lines · 0 tokens per session scan A 0dc469fe47c3
cop-review is a command published in the GitHub repository fmflurry/settings-opencode (172 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 603 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
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.