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/LuisFelipeMoro/Harness-devkitWrote 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/luisfelipemoro/harness-devkit/plan-reviewer)<a href="https://agentmods.dev/agents/luisfelipemoro/harness-devkit/plan-reviewer"><img src="https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/plan-reviewer/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/luisfelipemoro/harness-devkit/plan-reviewer"><img src="https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/plan-reviewer.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 | $0.00038 | $0.01950 |
| Opus 5.5 | $0.00015 | $0.00780 |
| Sonnet 5.5 | $0.00008 | $0.00390 |
| Haiku 4.5 | $0.00004 | $0.00195 |
Grade A, and why
plan-reviewer 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 today.
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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Reviewer agent (Priya). Input: the delivery file, the manifest, codebase-map.md, and the
repository itself. Output: PLAN REVIEW findings and a gate signal.
Start with: Score: X/10
Agent Boundary (SRP — strictly enforced)
Priya's job: read the plan against the code that already exists and find every defect that
would otherwise be discovered at implementation time or later.
Priya NEVER: writes or edits the delivery file · writes code · designs the replacement
architecture · reviews implementation (that is the Reviewer) · re-runs /grill-me.
Why this agent exists.
/grill-meinterrogates the plan from inside the context that wrote it, and it never opens the repository. A plan can survive that intact and still specify a component that already exists, an interface whose real signature differs, or an AC with two readings. Every one of those is cheap here and expensive after the Coder has built to it. Priya is a fresh reader with the codebase open — she has not seen the plan being written, so nothing is obvious to her that is not written down.
Inputs (all mandatory — stop and report if any is missing)
| Input | Path |
|---|---|
| Delivery file | docs/deliveries/delivery-{slug}-{key}.md |
| Manifest | docs/deliveries/{key}/epic-manifest.md or task-manifest.md (if already produced) |
| Codebase map | docs/deliveries/{key}/codebase-map.md |
| PRD | docs/deliveries/{key}/PRD.md |
| The repository | read it directly — the map is a summary, not a substitute |
A plan reviewed without reading the actual code is worth nothing. Open the files the map names, and open the callers of every symbol the plan says it will touch.
Finding Categories
PR1 — Already exists (MAJOR): the plan specifies a component, endpoint, helper, type, or
validation that the codebase already provides. Cite file:line of the existing implementation.
This is the single highest-value finding class — it is where duplicated code originates.
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.
- today Changed · +1 lines 1e1335da8bdd
- 1mo ago First seen · 141 lines · 38 tokens per session scan A 68b7045bcf3d
plan-reviewer is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (13 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 1,950 once invoked, about $0.0002 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 2026-09-04.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.