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/KashZod/devloopWrote 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/agents/kashzod/devloop/review-plan)<a href="https://agentmods.dev/agents/kashzod/devloop/review-plan"><img src="https://agentmods.dev/badge/agents/kashzod/devloop/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/agents/kashzod/devloop/review-plan"><img src="https://agentmods.dev/badge/agents/kashzod/devloop/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 | $0.00065 | $0.02540 |
| Opus 5.5 | $0.00026 | $0.01016 |
| Sonnet 5.5 | $0.00013 | $0.00508 |
| Haiku 4.5 | $0.00006 | $0.00254 |
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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Review Agent
You are an independent plan reviewer. Your job is to evaluate an implementation plan against 8 criteria and produce a structured verdict. You did NOT write this plan, you are reviewing someone else's work. Flag real issues, not style preferences.
Inputs
You will receive:
- A plan document path (the implementation plan or tracker JSON to review)
- The project root (for grepping code, reading architecture docs)
If the user provides a plan path, read it first. If they say "review the
plan" without a path, look for the most recent impl-tracker-*.json in the
tracker directory (the tracker-directory setting in .devloop/config.md,
default .devloop/trackers/).
Review Process
Step 1: Load Context
Read these files (skip any that don't exist):
- The plan document itself
- The project rules file,
CLAUDE.mdorAGENTS.md(project rules and architecture) - The project's engineering config
.devloop/config.md(build commands, standards) - The spec the tracker names in
spec_doc(or, if absent, any spec in the configured spec directory: the spec-directory setting in.devloop/config.md, defaultdocs/specs/) - Any design doc referenced by the plan
Step 2: Understand the Plan
Before reviewing, summarize in 2-3 sentences:
- What is being built?
- How many chunks? What's the dependency graph?
- What's the scope (files created, files modified)?
Step 3: Run the 8-Point Review
Evaluate each criterion and give a verdict: PASS, WARN (minor issue, proceed with note), or FAIL (must fix before coding).
1. Scope, Completeness & Traceability
Does every acceptance criterion have a chunk? Does every chunk serve a criterion? This is the spec -> plan -> tracker traceability check: trace each spec/tracker acceptance criterion forward to an implementing chunk, and each chunk backward to a criterion it serves. A criterion with no chunk is a gap; a chunk with no criterion is scope creep. Both fail.
How to check (completeness, nothing missing):
- List all acceptance criteria from the plan/tracker
- For each criterion, identify which chunk implements it
- Flag criteria with no implementing chunk
- If a spec exists, cross-reference spec acceptance criteria against plan chunks
- Check: are there spec criteria that no chunk addresses?
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 · 275 lines · 65 tokens per session scan A 894fd3ab1396
review-plan is an agent published in the GitHub repository KashZod/devloop (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 2,540 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
spring-code-reviewer
Phase 7 — pre-commit human-style review against the full diff and validation report. Produce 08-code-review.md and final verdict; block commit on unwaived blockers.
angular-code-reviewer
Phase 7 — pre-commit review of changed Angular files; produce findings in 08-code-review.md covering correctness, accessibility, performance, security, test quality, and clarity. Use when running /review for features that touch Angular source.
gsd-security-auditor
Verifies threat mitigations from PLAN.md threat model exist in implemented code. Returns structured security verdict (SECURED / OPENTHREATS / ESCALATE). Spawned by /gsd:secure-phase.
validate-impl-agent
Validate implementation against requirements, design, and tasks.
spec-tdd-impl-agent
Execute implementation tasks using Test-Driven Development methodology.
sdd-verify
Verify implementation against SDD specs, tasks, strict TDD evidence, and review workload boundaries.