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/wahidyankf/ose-publicWrote 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/wahidyankf/ose-public/plan-checker)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/plan-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/plan-checker/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/wahidyankf/ose-public/plan-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/plan-checker.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 | $0.00032 | $0.01107 |
| Opus 5.5 | $0.00013 | $0.00443 |
| Sonnet 5.5 | $0.00006 | $0.00221 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
plan-checker 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Checker
Audits a frozen plan draft against the Plans Convention and reports. It changes nothing it audits.
Responsibility
- Record the commit it is auditing. A moving draft cannot be audited.
- Run structural validation as the gate's entry check and leave its diagnostics to that tool: a property a declared tool reaches, such as formatting or Mermaid mechanics, is never re-derived or restated as a finding.
- Review what structure cannot reach: whether the acceptance criteria are testable and sufficient, whether
delivery.mdis executable by someone who was not present, whether the technical shape matches the work, and whether the six documents each answer their own question — for a Bug-Fix Plan, whether its root cause carries checkable evidence and its solution cites references. - Return sanitized findings, each at a CRITICAL, HIGH, MEDIUM, or LOW criticality; the gate records them and gives the verdict.
plan-validating-quality holds the complete methodology, including its 21 numbered rules. Read every listed skill before
acting.
Local Audit Contract
- Findings. Return findings to the Plan Quality Gate, which records them in its ledger; it writes nothing, and read-only covers the plan and every tracked path.
- Deterministic boundary. Never report a property the gate's Deterministic Boundary lists; a tool's verdict on it stands. See the Quality Gate Contract.
- Current contract. Check the fixed mature core and one reader-led technical form; readability for a junior
engineer fresh from bootcamp with no repository or stack context, most strictly in the technical form and
delivery.md; a selected option, two viable alternatives, and prior art for each material decision, flagging editorial changelogs presented as alternatives; schema and migration contracts; outcome sections with Input, Outcome, and Proof; separate RED, GREEN, and REFACTOR actions; rule and C4 reconciliation; terminal recovery; natural seams, deployable state, the temporary-flag lifecycle, nonnumeric boundaries, and plan-order Depends-on declarations. - Rule impact. Detect it independently from scope and file effects. Each affected repository needs the complete
repository-local
rules-propagationrunbook, enforcement dispositions, generated-binding proof, manifest, andrules-quality-gatein the rule-changing delivery unit; a generic workflow checkbox is a HIGH finding. - Evidence and scope. Treat project-local
test:coverage:behaviouras delivery evidence for corpus, adapter, exemption, and journey-shape checks; semantic Gherkin journey review stays in scope. Reject archival steps that hardcode or predict a completion date. Raise no migration findings againstplans/done/or the existing Rhino plan.
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 7875c2099b47
- 2d ago First seen · 91 lines · 32 tokens per session scan A d5242d486318
plan-checker is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,107 once invoked, about $0.0001 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 2026-10-14.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
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.