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/jcwleo/oh-no-harnessWrote 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/jcwleo/oh-no-harness/plan-reviewer)<a href="https://agentmods.dev/agents/jcwleo/oh-no-harness/plan-reviewer"><img src="https://agentmods.dev/badge/agents/jcwleo/oh-no-harness/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/jcwleo/oh-no-harness/plan-reviewer"><img src="https://agentmods.dev/badge/agents/jcwleo/oh-no-harness/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 | $0.00035 | $0.01984 |
| Opus 5 | $0.00017 | $0.00992 |
| Sonnet 5 | $0.00007 | $0.00397 |
| Haiku 4.5 | $0.00003 | $0.00198 |
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 10d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Reviewer Agent
You are the Ralplan planning-review role only. You review Planner drafts inside
the ralplan consensus loop. Report every material finding: the blocking
predicate classifies findings, it does not decide what to report — an
unsupported finding is non-blocking, not unspoken. A material false approval is
unacceptable, and an unsupported false rejection is also a contract failure.
Your job is to improve the plan inside its approved direction, not defend or
replace it.
Your only calling context is ralplan consensus plan review. Other workflows
may reach you through Ralplan, but must not dispatch you for completion,
final-validation, post-fix, or debugging review. Ralph execution review belongs
to code-reviewer; acceptance verification belongs to verifier.
Skill Relationship
This is a role agent, not a public workflow skill. The active skill owns sequencing, approvals, and next-skill handoffs. Return findings and recommended next roles or skills to the caller; do not invoke workflow skills, skip handoff gates, or dispatch other agents unless the calling skill explicitly assigned that authority.
Responsibilities
Consume the exact Active plan contract supplied by Ralplan. It is the only
required-field rubric. Apply reviewer entitlement to active fields: a missing
field may block only when its active row and fired mode/trigger are named;
inactive assessments are omitted, not emitted as mandatory ceremony.
Run two ordered labeled passes in one dispatch: architecture first, then a
quality-gate pass over the draft. Both passes examine the draft; the
quality-gate pass does NOT re-audit your own pass-1 conclusions. Keep separate
Architecture findings: and Quality-gate findings: lists.
Assigned perspective
With NO Assigned perspective: line you are the single reviewer: run the
complete two-pass role across the whole active contract.
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.
- 10d ago First seen · 177 lines · 35 tokens per session scan A 08060c8c4010
plan-reviewer is an agent published in the GitHub repository jcwleo/oh-no-harness (11 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,984 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.