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/adobe/spacecat-api-service/branch-reviewgit clone --depth 1 https://github.com/adobe/spacecat-api-serviceWrote 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/adobe/spacecat-api-service/branch-review)<a href="https://agentmods.dev/commands/adobe/spacecat-api-service/branch-review"><img src="https://agentmods.dev/badge/commands/adobe/spacecat-api-service/branch-review.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00531 |
| Opus 5 | $0.00006 | $0.00266 |
| Sonnet 5 | $0.00003 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
Review Branch 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 4d 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.
What it actually says
Review the branch {{branch_name:current}} against {{base_branch:origin/main}}.
Review Process
- Get Context: Fetch latest origin/main, then run git diff and log commands to understand the changes
- Apply Rules: Review against @.github/copilot-instructions.md and applicable rules in @.cursor/rules/
- Critical Checks: Follow severity definitions and core checks from copilot-instructions.md
- Output: Provide structured markdown review below
Output Format
# Code Review: [Branch Name]
## Summary
[1-3 sentences describing overall health of the PR]
## Issues
### Critical
[Issues that block merge - bugs, security, missing tests for behavior changes, missing access control]
### Major
[Issues that should be fixed - missing docs, performance concerns]
### Minor
[Optional improvements - only list if no Critical issues exist]
## Suggested Tests
[Describe missing test coverage if applicable]
## Checklist Review
- [ ] **Security & Authorization**: AccessControlUtil instantiated and called (hasAdminAccess/hasAccess)
- [ ] **Bug & Regression**: Null checks, async/await, logic changes match tests
- [ ] **Routing**: Endpoints in BOTH src/index.js and src/routes/index.js
- [ ] **UUID Validation**: All IDs validated with isValidUUIDV4
- [ ] **DTOs & Models**: DTOs used, no raw database models leaked
- [ ] **Tests**: Behavior changes covered, fixtures updated
- [ ] **HTTP Helpers**: Using @adobe/spacecat-shared-http-utils
- [ ] **Shared Utils**: Using @adobe/spacecat-shared-utils instead of custom checks whenever possible
- [ ] **Documentation**: OpenAPI specs if endpoints changed, README, config/default.json updated for new features
## Final Assessment
**Status:** [READY TO MERGE | REQUIRES FIX | BLOCKED]
[Brief explanation and estimated fix time if issues exist]
Important
- DO NOT post comments to GitHub
- FOCUS on Critical issues first per copilot-instructions.md
- CITE specific files and line numbers for issues
- OUTPUT the structured markdown review above for discussion
- THEN propose specific code changes to fix Critical and Major issues
- REFERENCE the review findings when proposing 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.
- 4d ago First seen · 63 lines · 13 tokens per session scan A 981d7094ea38
Review Branch is a command published in the GitHub repository adobe/spacecat-api-service (10 stars, last pushed 5d ago), licensed Apache-2.0. It adds 13 tokens to every session and 531 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
git
Git operations with intelligent commit messages and workflow optimization.
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.